claude

dossier

Evidence-first project documentation system. Produces an audit-ready 23-file package for technical due diligence, engineering and product onboarding, and partner or customer communication — every material claim traced to a ledger row and a claim state, three context-isolated verification passes, and a binary release gate. Ships a post-merge GitHub Actions job that keeps the package current by opening a documentation PR. Requires bash, git and jq; on Windows, Git Bash (see docs/windows-support.md).

7 on GitHubby Daniel Bentesv1.2.2Apache-2.0updated yesterdaydocumentation
/

Plugin dossier from marketplace synapti-marketplace in synaptiai/synapti-marketplace. Commands read from the repo's manifest — today.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (10)

  • disclosure-gating

    Gate every externally-visible sentence through the claim and disclosure register in `00-control/claim-and-disclosure-register.md` (`CL-####`), then derive `06-public/technical-partner-guide.md` and `06-public/customer-product-and-trust-guide.md` from approved rows only. Use when drafting or editing

  • doc-package-contract

    Enforce the fixed 23-file, 8-directory documentation package under the resolved output root — routing each document to its required-content contract in `references/package-contract-*.md`, stamping the internal or public header, and refusing to add, drop, rename, or merge a canonical file. Use when s

  • engagement-scoping

    Resolve the documentation engagement scope from the settings cascade — project identity, source roots, output root, delivery mode, action ceiling, confidentiality default, and the exact file set this run may touch — and freeze it to `<outputRoot>/00-control/.scope.json`. Use when any /dossier:* comm

  • evidence-ledger

    Record every material claim as a row in `00-control/evidence-ledger.md` carrying a source-authority level and a claim state (verified, corroborated, reported, inferred, unknown, not applicable), and keep observed, interpreted, unknown, and recommended content in visibly separate blocks. Use when inv

  • finding-reconciliation

    Merge the independent A/B/C findings tables into one adjudicated ledger in `07-verification/documentation-verification-report.md` — normalizing to the finding schema, deduplicating by location and claim, recording per-finding corroboration without downgrading single-pass findings, promoting cross-pa

  • gap-and-contradiction-register

    Maintain `00-control/assumptions-questions-and-contradictions.md` — the assumptions and open-questions register (`AQ-####`) and the contradiction register (`CT-####`) — classifying each entry as blocking, material but non-blocking, or minor, and routing blocking gaps to owner resolution before draft

  • project-modeling

    Build one canonical project model — entities, boundaries, owners, lifecycle state, and end-to-end traces — and record its authoritative names in `00-control/terminology-and-ownership.md` (`TM-####`), then project that single model into every audience view without ever forking it. Use when starting P

  • prose-clarity

    Rewrite and self-check drafted prose against a machine-checkable clarity standard derived from ASD-STE100 (Simplified Technical English) — no marketing adjectives, no phrasal verbs, no semicolons, active voice, short sentences, and a required carve-out for the epistemic hedge markers the evidence le

  • scoring-and-release-gate

    Score a documentation package against the ten-dimension weighted rubric in `references/scorecard-rubric.md` with a cited justification per dimension, then evaluate the nineteen conditions in `references/release-gate-conditions.md` and emit a binary release-ready, conditionally-ready, or not-ready ve

  • verification-protocol

    Run one independent verification pass over a documentation package by attempting to falsify it — a coverage inventory rebuilt from the contracts rather than the index, a two-stratum claim sample, end-to-end traces executed against the sources, audience task simulation, and mechanics validation — emi

Slash commands (9)

  • /dossier:audit

    Run the three independent verification passes over a documentation package. Dispatches evidence, falsification, and audience lenses in isolated contexts and collects their findings tables verbatim. Does not merge, judge, or repair — that is /dossier:reconcile.

  • /dossier:baseline

    Build the full documentation package from evidence. Inventories sources, models the project, resolves material gaps, drafts the 21 internal documents in dependency waves, then derives the 2 public documents from approved claims only.

  • /dossier:claim

    Adjudicate whether a single statement may be said publicly. Traces the claim to its evidence, checks the claim state and disclosure approval, and returns approved, needs-evidence, or blocked with the exact qualification required.

  • /dossier:gate

    Evaluate the nineteen release-gate conditions and issue a release-ready, conditionally-ready, or not-ready verdict. Runs the mechanical checks by script and dispatches the scorer for the judgment set — and refuses to pass without both.

  • /dossier:init

    Initialize a dossier documentation package. Resolves the engagement inputs, classifies the project from evidence, writes .claude/settings.dossier.json, scaffolds the 23 canonical files, and seeds the five control registers.

  • /dossier:reconcile

    Merge the independent A/B/C findings into one adjudicated ledger, publish the pre-repair table, apply agent-repairable corrections, route owner decisions to the registers, and trigger a re-audit when a material claim changed.

  • /dossier:refresh

    Refresh the documentation package for a range of changes. Computes the blast radius from changed evidence, re-inventories only what moved, re-drafts the affected documents and everything downstream of them, then sweeps the whole package for contradictions. The entry point the post-merge CI job invok

  • /dossier:setup

    Wire the post-merge documentation refresh into this repository. Preflights the GitHub settings that silently break it, renders the three-job workflow, creates labels, and lists the manual steps setup cannot perform.

  • /dossier:status

    Read-only overview of documentation package health — canonical coverage, register counts, open material gaps, staleness against the freshness threshold, the last gate verdict, and whether the post-merge automation is wired and current.

Subagents (6)

  • dossier-doc-drafter

    Draft exactly one canonical package document from its required-content contract, the project model, and the evidence-ledger slice it is given, citing evidence IDs on every material assertion and marking claim states. Use when Phase 4 drafts internal documents or Phase 5 derives public documents, dis

  • dossier-evidence-collector

    Inventory a project's sources and emit evidence-ledger rows with source-authority levels and claim states, without drafting any prose. Use when Phase 1 of a baseline needs an evidence inventory, or when a targeted refresh needs fresh evidence for a blast-radius file set.

  • dossier-pass-a-evidence

    Independent verification pass A — coverage and evidence integrity. Rebuilds the required-file inventory from the package contracts rather than from the documentation index, audits the census claim categories at 100%, and verifies each sampled claim against its cited ledger row and the original sourc

  • dossier-pass-b-falsification

    Independent verification pass B — model falsification. Selects and executes end-to-end traces from the sources of truth (entry point through code path, data store, deployment, and observability) and attempts to break the documented project model, reporting every point where the package and the sourc

  • dossier-pass-c-audience

    Independent verification pass C — audience usability, consistency, and disclosure. Simulates each named reader completing their task using only the package (day-one engineer, diligence lead, product manager, on-call responder, security reviewer, partner integrator, customer trust reviewer), then val

  • dossier-scorer

    Issue the independent scorecard and the binary release-gate verdict for a documentation package, seeing only the final package, the adjudicated findings ledger, and the resolved scope — never the drafting or repair rationale. Use when reconciliation and repair are complete, or when CI needs a machin

Hooks (5)

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/enforce-output-root.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/block-unregistered-claim.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/enforce-allowed-actions.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/stale-header-stamp.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/detect-local-merge.sh

View source on GitHub

More from synaptiai/synapti-marketplace

All 9 plugins →

flow

claude

Skill-driven workflow plugin for GitHub development with excellence-by-default quality gates. Encodes team knowledge as composable skills, enforces safety through hooks, compounds learning across sessions, and provides durable goals, workflows, triggers, and runs at .flow/. Requires bash, git, gh, jq, and python3 with PyYAML; on Windows, Git Bash (see docs/windows-support.md).

33 skills · 23 commands · 10 agents · hooks

7

Grounded Agency: 36 atomic capabilities with typed contracts, safety-by-construction, and grounded reasoning for reliable AI agents

42 skills · hooks

7

Generic GitHub workflow commands for issue management, PR creation, code review, and releases. Works with any repository by auto-detecting settings.

7 skills · 14 commands · 4 agents

7

Evidence-based product development with traceable decisions, constrained spec generation, and impact-aware updates. Forces auditability through semantic IDs and quality gates.

5 skills · 8 commands · 5 agents

7

Fourteen opinionated skills for designing, deploying, adopting, and evolving AI-first organizations — diagnose coordination overhead, encode organizational identity, write specifications, convert approvals to quality gates, validate gates against hidden holdout scenarios, architect governance, redesign roles, navigate politics, operationalize designs into agent-consumable primers, run evolution audits, generate agent configurations, build per-role maturity matrices, design adoption sprints, and write human-facing AI usage policies.

15 skills

7

decipon

claude

NCI manipulation detection with deep research fact-checking - analyzes content for propaganda, disinformation, and manipulation patterns across 20 categories with integrated claim verification

2 skills · 7 commands · 5 agents

7

Similar plugins

Claude API and SDK documentation skill for building LLM-powered applications

19 skills

anthropics/skills 193,780

AI-powered codebase understanding — analyze, visualize, and explain any project

9 skills · 10 agents · hooks

Egonex-AI/Understand-Anything 92,410

ruflo-adr

claudecodex

ADR lifecycle management — create, index, supersede, and link Architecture Decision Records to code

5 skills · 1 command · 1 agent

ruvnet/ruflo 81,589

Generate natively editable PPTX from PDF / DOCX / URL / Markdown — real DrawingML shapes, text boxes, charts, and animations. Note: run `pip install -r requirements.txt` inside the installed plugin directory for the Python post-processing scripts to work.

1 skill

hugohe3/ppt-master 76,375

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Install the "AAS Documents & Presentations" workflow plugin from Agentic Awesome Skills.

7 skills

sickn33/agentic-awesome-skills 49,620

Maintain dossier?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins9 plugins