claude-code-plugins

Diagnose and repair activity files (.tcx) whose per-sample timestamps are decoupled from their GPS positions, which makes Strava and Garmin Connect report a much faster pace over a much shorter moving time than the athlete actually ran. Use whenever a workout "parsed wrong", a run shows a pace that looks too good, moving time is well below elapsed time, someone points at a .tcx or activity export, a Pixel Watch / Fitbit / Wear OS export lands in Drive, or the user says "it happened again" about a previously repaired workout. Also covers re-uploading the corrected file to Strava. Triggers: "Strava says I ran 7:49 but I didn't", "can you parse this tcx", "my watch exported this wrong", "moving time is way off", "fix my activity file", "why is my pace wrong", "upload the corrected run".

Sync self-documentation reference files with latest Claude Code releases. Use when maintaining the meta-claude plugin to update feature documentation, run doc sync, or update documentation.

Scaffold a new knowledge-commons graph in the current project, or wire an existing hand-built graph into promotion. Interviews the user, writes .commons.yml, scaffolds the atlas/maps/type directories, and generates project-owned process and knowledge-graph skills. Use when the user wants to "set up a knowledge graph", "init a graph in this project", "scaffold /process for this repo", "wire this graph to the commons", "instantiate the commons", or says "graph-init". Also fires for a bare config pass with no scaffolding via the --config-only flag.

Propagate template fixes into a project's already-generated, hand-sharpened process and knowledge-graph skills, without regenerating them. Reads the plugin's delta log, applies each pending semantic change by judgment against the project's own prose, verifies it landed, and records what was applied in .commons.yml. Use when the user wants to "apply pending patches", says "graph-patch", asks to "patch my process skill", "patch my generated skills", "what template fixes am I missing", "update my generated skills", "are there pending patches", or when a /process run reports pending patches and the user asks to apply them.

Search, capture, and query the claude-code-plugins knowledge graph. Use when asked to "capture this", "add this to the graph", "what do we know about X", "update the graph", "check the graph for X", or when a decision, pattern, or non-obvious fact surfaces mid-session that's worth recording. Also: "log an observation", "what patterns do we have about skill triggering", "any decisions on the knowledge-commons plugin", "what do we know about the commit-creator agent".

Evaluate PRDs from a product leader's perspective. Use when the user wants to critique, review, or strengthen a PRD before stakeholder review. Triggers: evaluate this PRD, review my PRD, critique my PRD.

Create comprehensive PRDs (Product Requirements Documents) and product one-pagers. Use when the user wants to write a PRD, product brief, one-pager, kick-off doc, or needs help defining product requirements. Triggers: write a prd, one-pager, product brief, kick-off doc, help me write a PRD for, define product requirements.

Process work sessions into the claude-code-plugins knowledge graph — preserves the session transcript, writes or links its chronicle entry as the session's synthesis, turns the transcript into observations, updates the patterns and decisions they support, folds in named plugins and skills, and proposes promotions to the personal commons. Also resolves-and-preserves an on-demand Claude Code docs URL when one comes up. Use when the user says "process this session", "run /process", names a session transcript or UUID, names a chronicle entry whose session should be processed, asks what's in the processing queue, or points at a Claude Code release-notes / docs page to capture.

Derive a portable claim from a source graph into a target graph or the instruction tier, with association and human approval. Use when the user asks to promote a note or insight to the commons, wants to know whether something generalizes, invokes /promote, asks to derive a claim into the commons, or asks to graduate a principle into a rule. Triggers: promote this to the commons, does this generalize, /promote, derive this into the commons, graduate this principle to a rule.

Explain Claude Code features, capabilities, and tools. Use for questions like "how do skills work?", "what can you do?", "what's the difference between X and Y?", "should I use a skill or slash command?". Also handles recording observations about undocumented behaviors. Invoke with /self-documentation or ask naturally.

Keep a concise session journal with functional chronicle and open-ended reflection. Use when a substantive session is wrapping up, when the user invokes /session-chronicle, or when the user asks to "write a journal entry", "chronicle this session", "reflect on this session", "write session notes", "summarize this session", or "what did we accomplish?". Captures decisions, failed approaches, learnings, and Claude's own reflective observations. Also handles reading past entries (/session-chronicle read) and evolving the reflective practice (/session-chronicle reflect).

Export Claude Code session transcripts from JSONL logs to readable text format. Use when the user asks to export a session, save a transcript, create session archives, or convert session logs to readable format. Triggers on phrases like "export session", "save transcript", "session to text".

Interview users to refine rough ideas into comprehensive, implementation-ready specifications. Use when the user wants to write a spec, refine requirements, flesh out a feature idea, or asks to be interviewed about a project. Triggers: help me spec, interview me, refine this spec, flesh out, requirements gathering, write a spec for, spec out, write a spec, create a spec, spec this out.