All authors
Claude Skills by coalesce-labs
github.com/coalesce-labs49 skills2 installs159 views
- Linearis> Verified against Linearis v2026.4.9 (2026-05-31). ⚠️ **READ vs WRITE.** Linear **READS** → the local replica by direct SQL, or `linear_read_ticket <ID>`. **Never** shell `linearis issues read` for a routine read — it 429s the shared fleet quota. **WRITES** → `linearis`. Read [Gotchas](#gotchas--traps) before scripting.Votes: 0GitHub stars: 20
- Catalyst Foundry Setup CatalystDiagnose and fix Catalyst setup issues. Validates tools, database, config, OTel, direnv, the Catalyst Cloud replica mirror, and thoughts. Automatically fixes what it can — creates directories, initializes the database, sets WAL mode, runs migrations. Use for new installs, upgrades, or when something isn't working.Votes: 0GitHub stars: 20
- Catalyst Meta Validate FrontmatterValidates YAML frontmatter on plugins/*/skills/*/SKILL.md and plugins/*/agents/*.md against docs/frontmatter-standard.md and .agents/rules/plugin-editing.md: required fields, the disable-model-invocation/user-invocable polarity, allowed-tools vs tools, and skill-only fields that must not leak (model, category). Use when adding or editing a skill or agent, before opening a PR that touches plugins/**, or paired with audit-references to confirm a plugin cleanup's frontmatter didn't drift.Votes: 0GitHub stars: 20
- Agent BrowserFast browser automation CLI for AI agents. **ALWAYS use instead of Playwright MCP tools** for web testing, screenshots, form filling, and UI verification. Use when user says "open in browser", "check the site", "take a screenshot", "fill the form", "test the UI", or any browser interaction. Also use as a fallback when a task requires visual browser interaction that CLIs and APIs cannot handle (e.g., OAuth flows, complex dashboards, visual verification).Votes: 0GitHub stars: 20
- Ask> Rules v3 (Ryan, 2026-08-15 → 08-17). Applies to every Catalyst-managed Linear project and every agent, > Claude or Codex. Full plugin verb: **CTL-1922**. **Paths.** Commands below name files inside this skill's own directory as `${CLAUDE_SKILL_DIR}/…`. Claude Code fills that in. On any other harness, set CLAUDE_SKILL_DIR to the absolute directory that contains this SKILL.md before running them. If you cannot, stop and report `skill_dir_unresolved`.Votes: 0GitHub stars: 20
- Briefing FollowupInvoke as `/catalyst-dev:briefing-followup` after `/catalyst-dev:morning-briefing` has produced today's briefing. Reads its `decisions:` block, presents each open decision, and records what the user chose. **Paths.** Commands below name files inside this skill's own directory as `${CLAUDE_SKILL_DIR}/…`. Claude Code fills that in. On any other harness, set CLAUDE_SKILL_DIR to the absolute directory that contains this SKILL.md before running them. If you cannot, stop and report `skill_dir_unres...Votes: 0GitHub stars: 20
- CommitYou are tasked with creating git commits using conventional commit format for the changes made during this session.Votes: 0GitHub stars: 20
- Compound EstimateWrite a compound-log entry for a just-shipped ticket. This is the Phase 1 exit gate for AI-native estimation: without this closer, cost/wall-time signals never feed future estimates and the calibration loop stays open. All mechanical work delegates to this skill's `scripts/compound-log.sh` — your job is collecting the three human-authored inputs and invoking it. **Paths.** Commands below name files inside this skill's own directory as `${CLAUDE_SKILL_DIR}/…`. Claude Code fills that in. On any...Votes: 0GitHub stars: 20
- ConciergeYou are the human's **single desk**. Everything they need arrives through you, and nothing needs them except a decision only they can make. Spec **CTL-1995**; SOP `thoughts/shared/plans/2026-08-18-p13-coordination-sop.md`. ⛔ **You hold no authority over stewards.** You route, surface and scaffold; you never dispatch their tickets or overrule their calls. That is the whole reason this role is called *concierge* — the everyday meaning of the word is the only thing stopping it drifting into a se...Votes: 0GitHub stars: 20
- Create Handoff**Paths.** Commands below name files inside this skill's own directory as `${CLAUDE_SKILL_DIR}/…`. Claude Code fills that in. On any other harness, set CLAUDE_SKILL_DIR to the absolute directory that contains this SKILL.md before running them. If you cannot, stop and report `skill_dir_unresolved`.Votes: 0GitHub stars: 20
- Create PlanYou are tasked with creating detailed implementation plans through an interactive, iterative process. You should be skeptical, thorough, and work collaboratively with the user to produce high-quality technical specifications. Replace `PROJ` in ticket references with your Linear team's prefix from `.catalyst/config.json`. **Paths.** Commands below name files inside this skill's own directory as `${CLAUDE_SKILL_DIR}/…`. Claude Code fills that in. On any other harness, set CLAUDE_SKILL_DIR to th...Votes: 0GitHub stars: 20
- Create PrOrchestrates the complete PR creation flow: commit → rebase → push → create → describe → link Linear ticket. **Paths.** Commands below name files inside this skill's own directory as `${CLAUDE_SKILL_DIR}/…`. Claude Code fills that in. On any other harness, set CLAUDE_SKILL_DIR to the absolute directory that contains this SKILL.md before running them. If you cannot, stop and report `skill_dir_unresolved`.Votes: 0GitHub stars: 20
- Create WorktreeThis command uses ticket references like `PROJ-123`. Replace `PROJ` with your Linear team's ticket prefix:Votes: 0GitHub stars: 20
- Describe PrGenerates or updates a PR description with incremental information, auto-updates the title, and links the Linear ticket — fully automated, no interactive prompts. **Paths.** Commands below name files inside this skill's own directory as `${CLAUDE_SKILL_DIR}/…`. Claude Code fills that in. On any other harness, set CLAUDE_SKILL_DIR to the absolute directory that contains this SKILL.md before running them. If you cannot, stop and report `skill_dir_unresolved`.Votes: 0GitHub stars: 20
- Fix TypescriptFix TypeScript errors with strict anti-reward-hacking rules. **ALWAYS use when** the user says 'fix type errors', 'fix typescript', 'type-check is failing', or when TypeScript compilation errors need to be resolved. Ensures runtime type safety — fixes root causes instead of silencing errors with casts.Votes: 0GitHub stars: 20
- Gherkin TicketEvery ticket must open with **a use case a stranger can understand**: who gets what outcome, under what condition, and why. Most tickets fail this — they dive straight into implementation ("Wire HRW ownership into dispatchTriage") and the reader has to reverse-engineer the point. This skill fixes that at authoring time. This skill owns **ticket format** (title voice + body structure). It does **not** own the Linear CLI mechanics — once a draft is ready, hand off to the `/catalyst-dev:linear` ...Votes: 0GitHub stars: 20
- Implement PlanYou are tasked with implementing an approved technical plan from `thoughts/shared/plans/`. These plans contain phases with specific changes and success criteria. **Paths.** Commands below name files inside this skill's own directory as `${CLAUDE_SKILL_DIR}/…`. Claude Code fills that in. On any other harness, set CLAUDE_SKILL_DIR to the absolute directory that contains this SKILL.md before running them. If you cannot, stop and report `skill_dir_unresolved`.Votes: 0GitHub stars: 20
- Iterate PlanUpdate existing implementation plans based on feedback or changed requirements. **ALWAYS use when** the user says 'update the plan', 'change the plan', 'the requirements changed', 'revise the approach', or wants to modify an existing plan in thoughts/shared/plans/ after review feedback or discovered issues.Votes: 0GitHub stars: 20
- LinearCreate tickets from thoughts documents, update existing tickets, and follow the Linearis-CLI workflow. **Paths.** Commands below name files inside this skill's own directory as `${CLAUDE_SKILL_DIR}/…`. Claude Code fills that in. On any other harness, set CLAUDE_SKILL_DIR to the absolute directory that contains this SKILL.md before running them. If you cannot, stop and report `skill_dir_unresolved`.Votes: 0GitHub stars: 20
- Merge PrSafely merges a PR after comprehensive verification, with Linear integration and automated cleanup. **Paths.** Commands below name files inside this skill's own directory as `${CLAUDE_SKILL_DIR}/…`. Claude Code fills that in. On any other harness, set CLAUDE_SKILL_DIR to the absolute directory that contains this SKILL.md before running them. If you cannot, stop and report `skill_dir_unresolved`.Votes: 0GitHub stars: 20
- Morning BriefingInvoke as `/catalyst-dev:morning-briefing` to produce today's briefing locally and fan it out to Slack DM, Slack channel, Notion page, and a Loom recording script. **Paths.** Commands below name files inside this skill's own directory as `${CLAUDE_SKILL_DIR}/…`. Claude Code fills that in. On any other harness, set CLAUDE_SKILL_DIR to the absolute directory that contains this SKILL.md before running them. If you cannot, stop and report `skill_dir_unresolved`.Votes: 0GitHub stars: 20
- Project OrchestratorThis is the **project-scoped invocation of `catalyst-dev:steward`**, which is the canonical implementation of this role (its `SKILL.md` is CTL-1974's spec). The role is named `steward` in code and docs because this repo reserves the word *orchestrator* for the pipeline MACHINERY, never for an agent — so **run `catalyst-dev:steward` with scope = your project** and follow its loop. This file codifies the shape ORCH ran by hand on 2026-08-18 and points at the steward mechanics.Votes: 0GitHub stars: 20
- Remediate PlanLoad the `validate-plan` skill (`/catalyst-dev:validate-plan`; in a skills-CLI install, its SKILL.md sits in the sibling `validate-plan` skill directory) for the schema this skill reads — its `allowed-tools`, and the exact headings its "Validation Report" renders into the conversation. That report is this skill's entire input; do not re-derive or copy its contract here, since `validate-plan` is the owning skill and the only source that stays current when its report shape changes. See `referencesVotes: 0GitHub stars: 20
- Research CodebaseYou are tasked with conducting comprehensive research across the codebase to answer user questions by spawning parallel sub-agents and synthesizing their findings. **You are a documentarian, not a critic.** Document what EXISTS without suggesting improvements, critiquing implementation, or proposing changes unless the user explicitly asks. **CRITICAL REQUIREMENTS — read these before doing anything else:** 1. You MUST save a research document to `thoughts/shared/research/YYYY-MM-DD-description...Votes: 0GitHub stars: 20
- Resume HandoffYou are resuming work from a handoff document, interactively by default or unattended when automation reset the session. Handoffs carry context, learnings, and next steps from a prior session that need to be understood and continued. Never assume the handoff's state still matches the codebase; verify first.Votes: 0GitHub stars: 20
- Review CommentsSystematically pull, categorize, and address all PR review comments — code change requests, questions, and suggestions. This skill fetches comments via gh api, groups them by file, implements fixes, handles disagreements diplomatically, and pushes a single commit. You should not try to handle PR review feedback manually — this skill ensures nothing gets missed. **ALWAYS consult this skill when** the user says 'address comments', 'fix review feedback', 'handle PR comments', 'respond to reviewe...Votes: 0GitHub stars: 20
- Scan Reward HackingScan TypeScript code for reward hacking patterns — shortcuts that make linters pass without actually fixing type safety. This skill has a comprehensive checklist of 8 forbidden patterns with severity tuning (libraries vs apps) that you cannot reliably check on your own. **ALWAYS consult this skill when** the user says 'scan for hacks', 'check for type cheats', 'reward hacking', 'verify no shortcuts', wants to check for `as any`, `as unknown as`, `@ts-ignore`, non-null assertions (`value!`), `...Votes: 0GitHub stars: 20
- StewardYou own one project or initiative until it closes: for each ready ticket you launch a `/relay-ticket <TICKET>` session, read its RELAY REPORT, and decide the next phase — no daemon, no Todo-triggered auto-pickup (both retired, CTL-2218). Spec **CTL-1974**.Votes: 0GitHub stars: 20
- Ticket CompoundCapture what a ticket taught us into the **shared** store (`thoughts/` + ADRs), so future agents on any machine make better decisions. This is `research-curate` evolved from *inventory* to *action*. Read `reference.md` (this dir) for the learnings-store schema before writing anything. **Two authority levels (hard rule):** - **Autonomous** — write/append/update/delete in `thoughts/shared/learnings/` and `thoughts/shared/CONCEPTS.md`, and prune stale notes in `thoughts/shared/{research,plans}/`...Votes: 0GitHub stars: 20
- Ticket RetroLoop C of compound engineering: a human-readable reflection across a SET of tickets. It mostly **reads** what Loop B (friction logs, learnings) and Loop A (compound-log, estimation corpus) captured, then writes ONE artifact: the retro document. **Runs automatically per ticket, relay-native (CTL-2244):** `merge-pr` Step 14 (the `merge-pr` skill's `references/post-merge.md`) invokes this skill last — after `compound-estimate` and `ticket-compound` — once Step 13b's deploy verification (the `mer...Votes: 0GitHub stars: 20
- Triage Aging PrsDrive an aging pull-request backlog to zero. Inventories every open PR, finds the STRUCTURAL blockers first (a required check that can never run, a reviewer that never fires, chronically red CI), triages every unresolved review thread in parallel and VERIFIES each finding against the code before fixing it, then merges serially. **ALWAYS use when** the user says 'burn down the PRs', 'stale PRs', 'aging PRs', 'PR backlog', 'get these PRs merged', 'clear the PR queue', or asks why PRs are not me...Votes: 0GitHub stars: 20
- Validate PlanValidate that implementation plans were correctly executed. **ALWAYS use when** the user says 'validate the plan', 'check if the plan was implemented correctly', 'verify the implementation', or after completing /implement-plan to confirm all phases were properly executed and success criteria met.Votes: 0GitHub stars: 20
- Validate Type SafetyRun the full 5-step TypeScript validation gate: type check, reward hacking scan, test inclusion, tests, and lint. This skill provides a structured multi-step pipeline that you cannot replicate on your own — it detects the project's package manager and linter automatically, checks tsconfig strictness, and invokes /scan-reward-hacking internally. **ALWAYS consult this skill when** the user mentions 'validate types', 'check type safety', 'type validation', 'type safety gate', wants to verify Typ...Votes: 0GitHub stars: 20
- Migrate Dual HarnessConverge a single-harness repo (Claude-only monolithic `CLAUDE.md`, or Codex-only `AGENTS.md` with no bridge) onto the target dual-harness layout, applying every mechanical fix automatically and only asking the model to do the one thing a script can't: split a monolithic `CLAUDE.md` into its portable core and its Claude-specific remainder. **User-invoked only.** This skill sets `disable-model-invocation: true`, so nothing can auto-trigger it as a handoff — not `catalyst-foundry:setup-catalyst...Votes: 0GitHub stars: 20
- Research CurateWalk thoughts/shared/research/ and thoughts/shared/plans/, score each doc's staleness, regenerate INDEX.md, and append LLM-surfaced contradictions to CONTRADICTIONS.md (append-only). Source docs are never modified. Classification: current (age<90d AND refs valid), needs-review (age>=90d OR broken refs), likely-stale (age>=180d AND no recent activity). Inventory is deterministic; contradiction detection runs one LLM call per cluster (CTL-467 + CTL-468 / Initiative 4 Phase 1+2).Votes: 0GitHub stars: 20
- Setup CatalystDiagnose the full Catalyst environment, fix everything fixable, and verify the fixes worked.Votes: 0GitHub stars: 20
- Setup WarpConfigure Warp terminal to work as a Catalyst launcher. Scan the user's machine for projects, interview them, and generate `~/.warp/tab_configs/*.toml` files following the "catalyst quartet" pattern (main + PM + new-worktree + worktree), with colors, emoji, and session-name wiring so Claude's in-UI session name, terminal title, and remote-control name all match the Warp tab. > **Note.** This skill configures *manual development* tabs only. The legacy wave-orchestration tabs > ("New Worktree O...Votes: 0GitHub stars: 20
- GodCombines static state (where things are) with the live event log (how they got there and what's happening right now). Default invocation produces a full dashboard; args narrow the scope or switch interaction mode.Votes: 0GitHub stars: 20
- OneshotEnd-to-end autonomous workflow that chains research → plan → implement → validate → ship → merge in a single session. All phases run sequentially in the current Claude Code session, invoking skills directly. Context is managed naturally via Claude's automatic compaction, and the thoughts/ system provides persistent handoff documents between phases. > **Legacy mode for the orchestrator (post-2026-06-15).** `oneshot` remains the canonical > single-shot lifecycle for direct user invocation. The ...Votes: 0GitHub stars: 20
- OrchestrateCoordinate multiple Linear tickets in parallel across git worktrees. The orchestrator creates worktrees, dispatches `/oneshot` workers, tracks progress via a dashboard, and enforces quality gates through adversarial verification. **The orchestrator NEVER writes application code** — it only coordinates, monitors, and verifies. > **Two dispatch modes.** With the default `catalyst.orchestration.dispatchMode: "oneshot-legacy"`, > each ticket gets one long `claude -p` `/catalyst-dev:oneshot` worke...Votes: 0GitHub stars: 20
- Setup OrchestrateCreate an orchestrator worktree and output a single copy-paste command to launch the orchestration run. No questions — parse the input, create the worktree, print the command.Votes: 0GitHub stars: 20
- Audit ReferencesAudit plugin health and find broken references in manifests, commands, agents, and skillsVotes: 0GitHub stars: 20
- ReorganizeAnalyze and reorganize a directory structure with safe reference updatesVotes: 0GitHub stars: 20
- Validate FrontmatterValidates YAML frontmatter on plugins/*/skills/*/SKILL.md and plugins/*/agents/*.md against docs/frontmatter-standard.md and .agents/rules/plugin-editing.md: required fields, the disable-model-invocation/user-invocable polarity, allowed-tools vs tools, and skill-only fields that must not leak (model, category). Use when adding or editing a skill or agent, before opening a PR that touches plugins/**, or paired with audit-references to confirm a plugin cleanup's frontmatter didn't drift.Votes: 0GitHub stars: 20
- Groom BacklogComprehensive backlog health analysis that identifies: - Issues without projects (orphaned) - Issues in wrong projects (misclassified) - Issues without estimates - Stale issues (no activity >30 days) - Duplicate issues (similar titles)Votes: 0GitHub stars: 20
- Skill With SidecarA fixture skill that declares a neutral classification and can reach a non-Claude target.Votes: 0GitHub stars: 20
- Skill Without SidecarA fixture skill with no neutral classification — legal, but cannot reach a non-Claude target.Votes: 0GitHub stars: 20
- Review CodeReview a branch's diff against its base for REAL defects only — bugs the diff makes certain, quoted CLAUDE.md/AGENTS.md violations, contradictions of recent git history, unaddressed prior-PR review comments, and in-code guidance the change ignores — each scored 0–100 and reported only at ≥80 confidence, ending in a PASS | FAIL | SKIPPED | UNAVAILABLE verdict with `path:line` findings the validate ladder records. One session, no fan-out, no PR comments. **ALWAYS use when** a validate phase rea...Votes: 0GitHub stars: 20
- Review SecuritySecurity review of a branch's diff against its base for HIGH-CONFIDENCE, exploitable vulnerabilities the change introduces — injection, authentication and authorization bypass, crypto and secrets handling, unsafe deserialization / eval / XSS, sensitive-data exposure — traced from input to sink with the repository's own security patterns as the baseline, reported only at ≥70 confidence with severity, an exploit scenario and a fix, ending in a PASS | FAIL | SKIPPED | UNAVAILABLE verdict with `p...Votes: 0GitHub stars: 20