spec-builder
claudecodexBuilds a selective BA specification set under docs/specs/ with stable requirement IDs and traceability, from any raw input, without inventing requirements.
1 skill
Bootstraps or standardizes the complete AI-agent harness for a repo - agents, path-scoped rules, commands, hooks, settings.json, docs tree, and AGENTS.md/CLAUDE.md - with a read-only audit mode as well.
Plugin harness-bootstrap from marketplace agent-harness-bootstrap in nguyenhx2/agent-harness-bootstrap. Commands read from the repo's manifest — 12 days ago.
harness-bootstrapBootstraps or standardizes the AI-agent harness for a repo - analyzes the existing source first, then generates the .claude folder (agents with explicit model/effort/tool budgets, path-scoped rules, commands, hooks, settings.json), the docs tree and AGENTS.md + CLAUDE.md, so one main session works e
/harness-bootstrap:agent-permissionsGrant or revoke a single tool on a single roster seat, with the invariants that keep the roster safe enforced - reviewers stay read-only, only the orchestrator spawns, model changes go through the roster file.
/harness-bootstrap:board-auditFind orphaned, stale, and loop-suspect work - Active tasks nobody is driving, finished subagent runs nobody logged, worktrees and branches the board does not know about.
/harness-bootstrap:code-graphBuild or refresh the module-boundary map - which modules may import which - and check the code against it. A new cross-module import is an interface decision; this is where it gets accepted.
/harness-bootstrap:docs-graphCheck DOCS traceability - which documents define which IDs, who references them, and which IDs are orphaned. Traceability, not dependency.
/harness-bootstrap:harness-toggleTurn one rule, command, hook, or agent seat off or back on in the current repo - reversibly, with the reason recorded and the harness graph refreshed.
/harness-bootstrap:harness-tuneTune the harness from evidence - reads the run archive, blocks and denials, retry and attempt-cap hits, verify-plan logs and the harness-view assessment, proposes a short ranked set of changes, asks once, applies the chosen ones and re-runs the check that proves each.
/harness-bootstrap:harness-updateRe-run the harness bootstrap on this repo to pick up new assets, add or retire agents, or re-derive scopes after the codebase changed - reconciling, never clobbering.
/harness-bootstrap:skill-wireWire an installed or newly created skill to a roster seat after re-vetting its content - scope match, mandatory content review, invariant refusals, a skills preload entry, and a changelog record. Skills serve nobody until wired.
Builds a selective BA specification set under docs/specs/ with stable requirement IDs and traceability, from any raw input, without inventing requirements.
1 skill
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
6 skills
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
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.