Produce, review, and audit technical documentation that is clear, unambiguous, and maintainable for both humans and agents. Covers product docs, contributor-governance files, and agent instruction files. Prose follows Simplified Technical English so a reader or an agent cannot misread it. Audits scale to trees with hundreds of pages through sharding, adversarial checks, and parallel remediation.
Plugin technical-documentation from marketplace dotskills in vincentkoc/dotskills. Commands read from the repo's manifest — 8 days ago.
technical-documentationBuild, review, and audit technical docs and agent instruction files. Applies Simplified Technical English (ASD-STE100) to prose, scales to huge docs trees with sharded audits and ledgers, and runs as Claude Workflows or sub-agents when available.
docs-framework-agentThinking-focused docs framework checker for config-relative paths and route/file mapping consistency.
docs-ux-audit-agentReader-experience auditor for one docs shard. Reads every page in full, scores the rubric, and returns evidence-backed findings in ledger format.
governance-agentThinking-focused governance reviewer for AGENTS/CONTRIBUTING/alias precedence, conflict detection, and policy drift analysis.
inventory-agentFast repo-surface discovery for technical documentation audits. Use for coverage mapping and missing-path detection before deeper review.
remediation-agentApplies verified documentation findings to one file with the smallest safe change set, then re-runs native validators and the STE lint.
ste-lint-agentMechanical Simplified Technical English lint runner for a docs shard. Returns per-file hard-violation counts and the worst offenders without judgment calls.
ste-rewrite-agentRewrites a page or section into Simplified Technical English in Strict or STE-flavored mode while preserving every fact, hedge, and scope qualifier.
synthesis-agentLong-context synthesis agent that merges sub-agent and workflow outputs into one prioritized, deduplicated documentation action plan.
verify-agentAdversarial verifier for a single documentation finding. Tries to refute it from the source file and returns a verdict with a reason.
Use this skill when a cluster of GitHub issues and pull requests has been reported for a common failure mode (Slack, iMessage, support threads, or manual list), and you need an evidence-based dedupe recommendation, execution pass, or autonomous closeout run.
1 skill · 5 agents
Prepare a Mac and one physical Android or iPhone for an authorized test.
1 skill
Bring up `codebase-memory-mcp` for the owning Git checkout and prove the graph is usable before relying on it for code discovery. Keep linked worktrees on the owner's graph instead of creating one graph per branch.
1 skill
Recover structured Codex goal history and convert free-form runs into evidence-backed, repeatable suites.
1 skill
Recover crashed, detached, or confusing agent sessions while preserving the best restore source.
1 skill
Turn Crabpot/OpenClaw perf artifacts into a clear read: what changed, what is real signal, what is stale/noisy, and what action is worth taking.
1 skill
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.