li

Plugin li from marketplace jokerman-lintel in jokerman89/lintel. Commands read from the repo's manifest — 1 month ago.

Skills (193)

• li-adr-new

  Use when a non-trivial decision needs recording to bootstrap a new Architecture Decision Record from the template, asking context-gathering questions to fill Status, Context, Decision, and Consequences. Reach for it whenever you've made or are about to make an architectural choice worth a durable re

• li-analyze

  Use to check that PLAN and BUILD still match the approved DEFINE design — run when a plan was revised or a build deviated, to catch drift between what was approved and what shipped. Checks the DEFINE-PLAN-BUILD legs and authority alignment, writes a severity-classified report, and is re-runnable rea

• li-audit

  Use to read selected audit records and diagnostics, including hook or usage observations, without inferring execution from missing logs.

• li-brief-forge

  Use when a workflow explicitly hands work across a boundary — spawning a subagent, transitioning a phase, passing to a cold executor, or taking operator input — to build a structured envelope and run the active pack's evaluators on it.

• li-build

  Use to implement an authorized plan card by card with spec and quality review and verification evidence.

• li-capture

  Use after delivery to record evidence, durable lessons and the next-session handoff.

• li-catalog

  Use to discover Lintel skills and agents by intent, name, purpose, category, voice or declared client support, or regenerate the committed skill catalog after frontmatter changes.

• li-clean

  Use for an honest context-weight readout and a pause/fresh-session/resume path when the current session feels heavy.

• li-cli-fingerprint

  Use to identify the current CLI, desktop, IDE or cloud surface and inspect its actual tools without inferring capability from a vendor name.

• li-code-freeze

  Use to add, list or lift advisory session freeze paths; preserves project policy and never grants or removes host write permission.

• li-code-review

  Use before landing a change to review just the diff — focused on the changed code only, lighter than a full engineering review. Reach for it when you have uncommitted or unmerged changes and want a correctness and quality pass before they land.

• li-compliance-gate

  Use when evaluating declared controls with mandatory, advisory, unverified and no-applicable outcomes; this is not host enforcement.

• li-context-budget

  Use before a large read or handoff, or when context headroom and resource advice are needed; keep observed usage, source estimates and unknown limits distinct.

• li-context-cool

  Exclude explicitly selected files from future context reads without claiming to remove already-sent conversation content.

• li-context-warm-customer

  Load customer-engagement repo state into context — their infrastructure-as-code, their CLAUDE.md, their ADRs, recent commits.

• li-context-warm-from-url

  Retrieve bounded external reference text only through explicit host policy and redirect checks, preserving source provenance and trust boundaries.

• li-context-warm

  Use to load bounded files, topic-related sources, ADRs or prior sessions with safe selection and honest input-size estimates before reading.

• li-cross-check

  Use for an independent second opinion on a diff, plan, code or hypothesis through an actually available authorized reviewer. Retains actor identity, disagreements and shared content-bound evidence without requiring a particular vendor.

• li-cycle

  Use for a multi-step initiative that needs the complete Lintel planning, implementation, review and capture cycle.

• li-da

  Use for data-architecture depth — schema design, migrations, sharding and partitioning, query-pattern audits, retention policy, and analytics readiness. Reach for it when the work turns on the data model or storage. Runs full, loop, or single-capability, dispatching to the data agents and scoring ag

• li-define

  Use when a request needs requirements, acceptance criteria and a concrete design before implementation.

• li-design-dna

  Use when a frontend or presentation task needs corpus-backed style, palette, typography or stack guidance, selected design-profile tokens, or static design and observed-color contrast checks.

• li-dh

  Use for devops and hosting depth — deployment plans, rollback strategy, observability specs, SLI/SLO budgets, capacity headroom, cost projection, and on-call playbooks. Reach for it when the work turns on how the system runs in production. Runs full, loop, or single-capability, dispatching to the op

• li-diagnose

  Use when something is broken and you don't yet know why — drives a hypothesis-led investigation that builds a minimum repro, eliminates variables, and isolates the root cause. Reach for it for "why is this failing?" before attempting a fix.

• li-discover

  Use to map an existing repository, relevant architecture and reusable components before planning changes.

• li-doctor

  Use to diagnose source, target, profile and installed-file integrity while keeping actual host activation explicitly unverified.

• li-eval

  Run the active pack's voice TEST against its voice CORPUS — per-cell accuracy → CALIBRATION.md.

• li-fix

  Use for a known bug with a clear fix path that needs to ship now — runs the abbreviated SENSE, BUILD, REVIEW, SHIP path and skips design, discovery, and planning. The hotfix shortcut; reach for it when the diagnosis is already done and only the fix remains.

• li-frontend-design-review

  Use to review built UI or produced frontend designs with actual route/viewport evidence, six canonical advisory dimensions and the existing required-control contract.

• li-frontend-design

  Use to direct frontend design, advise on a design-system choice or compare bounded variants while preserving the shared design contract and actual rendering/review evidence.

• li-frontend-motion

  Use when a frontend brief needs an animation, scrolling or reduced-motion strategy, including no-animation and CSS-only choices.

• li-frontend-shader

  Use when a frontend visual brief needs a shader or no-shader decision, source-backed library choices, performance limits and GPU fallbacks.

• li-frontend-style-extract

  Use to extract reusable layout, motion, interaction and component patterns from selected sites, screenshots or frontend source into an explicitly owned output.

• li-frontend-typography

  Use when a frontend brief needs font stacks, a type scale, variable-font axes or a loading strategy with source and licensing evidence.

• li-full-engineering-pass

  Use for a customer engagement or major release that needs the whole engineering picture at once — composes all five domain modules (architecture, data, security, devops, testing) in dependency order. One invocation produces architecture decisions, a data model, a security posture, an ops plan, and q

• li-generate-app

  Use when a resolved frontend design needs a Next.js, Vite-React or SvelteKit application scaffold that preserves the selected stack and dependency choices.

• li-generate-design

  Use when existing content needs layout mappings, a selected palette, fonts and asset placements for one or more document or web formats.

• li-generate-docs

  Use to generate source-grounded reference documentation, customer guides or onboarding tutorials while retaining API behavior, examples, provenance and limitations.

• li-generate-outline

  Use to turn a presentation or document brief into a structured outline before drafting its content.

• li-generate-pdf

  Use to produce a PDF from selected source content through an available converter or accepted browser print operation; Lintel does not read the produced PDF, so its text, pages and visual rendering stay unverified.

• li-generate-ppt

  Use to create an editable PowerPoint deck from a brief or shared pipeline, retaining source detail in notes and inspecting actual rendered slides.

• li-generate-qa

  Use to inspect generated or supplied artifacts against source, brand, readability and structure requirements without modifying them; explicitly requested repairs use a separate owned copy.

• li-generate-style-learn

  Use to extract a reusable palette and typography reference from selected presentation, document or web artifacts without modifying the sources.

• li-generate-visio

  Use when a request calls for architecture, network or process-flow diagrams through the Visio scaffolding slot; no curated generation workflow is supplied.

• li-generate-web

  Use to render a static HTML mockup, a profile-aware single-file page or a Next.js scaffold from a brief or the existing design/content contracts.

• li-generate-word

  Use to create an editable Word document from selected source material through available native tools or a declared library, preserving detail and reporting actual inspection evidence.

• li-generate-write

  Use when a presentation or document outline needs full section content and speaker notes in the selected voice.

• li-generate-xlsx

  Use to create an editable workbook from selected source data through available native tools, with formula, recalculation and persisted-cache checks and explicit inspection limits.

• li-generate

  Use to produce a finished document or deliverable from a brief — drives outline, writing, design, and QA through to a built artifact in a chosen format such as slides, Word, web, or PDF. Reach for it when the ask is to generate a polished document rather than write code.

• li-handoff-size-check

  Use for the retained handoff-budget entry point; delegates selected artifacts and supplied observations to context-budget.

• li-hooks-status

  Use to inspect recorded hook outcomes, overrides or unobserved hooks through the shared audit reader; absence is not an execution verdict.

• li-inspect

  Use to inspect a selected plan or repository through engineering, design and developer-experience lenses. Preserve original work and short-leaf acceptance, report concrete findings, and use shared content-bound evidence without treating scores as clearance.

• li-instruction-parity-check

  Use to verify shared session protocol equality and client-entry links without overwriting project prose or confusing similarity with authority.

• li-jobs

  Use when listing or steering repository-local jobs; job lifecycle observations do not replace selected work-map authority or establish all open work.

• li-lessons-add

  Use after a correction, insight, or recurring pattern worth remembering to record it as a lesson the next session will read at startup. Reach for it whenever the operator corrects you or you discover something that should prevent the same mistake recurring.

• li-lessons-promote

  Promote one ID-managed project lesson into an explicitly named Lintel work tree's scaffolding baseline, with recorded provenance and no implicit branch, commit or push.

• li-lessons-surface

  Use before or during a task for keyword-ranked lessons, the complete index or an exact lesson ID, without changing the memory store.

• li-maintenance

  Use for on-demand storage/context guidance, scoped path diagnostics and labeled usage estimates without treating partial logs as health or claiming model compaction.

• li-mars

  Use when a problem, plan, spec, implementation or review needs a deliberate multi-model adversarial review with bounded rounds and preserved dissent.

• li-migrations

  Read the installed-source migration catalog against the selected target, preserving overdue, unknown and historical recovery states.

• li-orientator

  Use for entry-time method guidance through catalog, preserving SENSE's existing pack navigation and high-risk confirmation.

• li-pack-create

  Use to create a blank, inherited, or cloned Lintel pack and validate it before activation.

• li-pack-list

  List configured-store, repository and installed-source packs with resolver precedence, validation results and the actual effective profile.

• li-pack-switch

  Use to explicitly switch the effective pack through the structured profile lifecycle, preserving required policy, configured paths and generation-bound recovery.

• li-pack-validate

  Validate a pack before activation or after editing its manifest. Checks effective required fields and inheritance with the shared resolver, then reports schema and version compatibility limits.

• li-pattern

  Use when recurring expectations should be captured, reviewed, versioned, shared or applied to named work as data-only patterns with explicit applicability, provenance and review traceability.

• li-pause

  Use before the context window fills up or before clearing the session to save the current state to a checkpoint file. Reach for it when a session is getting heavy and you want to preserve where you are so a later session can pick up exactly here.

• li-perf-mode

  Use for the retained resource-advice entry point on heavy work; delegates to context-budget without changing model capacity.

• li-perfbench

  Measure performance — runtime, memory, cold-start — and detect regressions vs baseline.

• li-plan

  Use to turn a design into a requirement-traced spec, dependency-ordered build cards and a cold-executor prompt.

• li-profile-switch

  Inspect host install state and guide explicitly supported activation or owned snapshot recovery, without inventing plugin controls.

• li-research

  Use when the operator wants to understand a domain, codebase or option space before committing to implementation. Runs the research-dive cycle — SENSE, DEFINE and DISCOVER — and stops with sourced findings, never BUILD or SHIP.

• li-resume

  Use to resume an interrupted initiative from its saved plan, state and handoff.

• li-review

  Use to review changes against the specification, engineering quality and the active policy.

• li-role-new

  Use to create a durable role through a guided interview or update its expertise with a reviewed-digest, sensitivity-aware change.

• li-role

  Use to take on or change a working role — activate one for a lightweight lens, turn it off, swap mid-session, apply its lens to an artifact, or load its full definition on demand. Reach for it when work would benefit from a specific role's perspective; one role is active at a time.

• li-roles-list

  Use to list configured role metadata and the current selection, with explicit consent before including private roles.

• li-safe-install

  Protect explicitly owned installation files with verified snapshots and conflict-preserving restore; announce recovery paths and refuse unowned rollback.

• li-sc

  Use for security and compliance depth — threat models, auth flows, secret management, dependency-security audits, compliance evidence, and incident runbooks. Reach for it when a change has a security or regulatory surface. Runs full, loop, or single-capability, dispatching to the security agents and

• li-scaffold-internal-tool

  Use for the retained internal-tool scaffold entry; delegates the selected CLI, service, dashboard or script intent to scaffold's owned method in internal-tool mode.

• li-scaffold-mvp
• li-scaffold
• li-scope
• li-sense
• li-ship
• li-skill-new
• li-skill-router
• li-spec-kit
• li-status
• li-swarm
• li-ta
• li-tq
• li-uniformity
• li-usage-log
• li-verify
• li-web-session
• li-welcome
• adr-new
• analyze
• audit
• brief-forge
• capture
• catalog
• clean
• cli-fingerprint
• code-freeze
• code-review
• compliance-gate
• context-budget
• context-cool
• context-warm-customer
• context-warm-from-url
• context-warm
• cross-check
• cycle
• da
• define
• design-dna
• dh
• diagnose
• discover
• doctor
• eval
• fix
• frontend-design-review
• frontend-design
• frontend-motion
• frontend-shader
• frontend-style-extract
• frontend-typography
• full-engineering-pass
• generate-app
• generate-design
• generate-docs
• generate-outline
• generate-pdf
• generate-ppt
• generate-qa
• generate-style-learn
• generate-visio
• generate-web
• generate-word
• generate-write
• generate-xlsx
• generate
• handoff-size-check
• hooks-status
• inspect
• instruction-parity-check
• jobs
• lessons-add
• lessons-promote
• lessons-surface
• maintenance
• mars
• migrations
• orientator
• pack-create
• pack-list
• pack-switch
• pack-validate
• pattern
• pause
• perf-mode
• perfbench
• plan
• profile-switch
• research
• resume
• review
• role-new
• role
• roles-list
• safe-install
• sc
• scaffold-internal-tool
• scaffold-mvp
• scaffold
• scope
• sense
• ship
• skill-new
• skill-router
• spec-kit
• status
• swarm
• ta
• tq
• uniformity
• usage-log
• verify
• web-session
• welcome

Hooks (9)

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/shared/session-digest/run.sh"

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/shared/no-secrets-in-edit/run.sh"

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/shared/secret-scan-block/run.sh"

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/shared/customer-data-block/run.sh"

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/shared/no-direct-main-push/run.sh"

• PostToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/shared/memory-budget-warn/run.sh"

• Stop

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/shared/cycle-incomplete-warn/run.sh"

• UserPromptSubmit

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/shared/cycle-position-inject/run.sh"

• UserPromptSubmit

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/shared/no-customer-data-in-message/run.sh"

Similar plugins