Spec Coach
Activate when the user is writing, editing, or discussing software requirements, specifications, acceptance criteria, user stories, or feature definitions. Also activate when the user asks to build, implement, or create a feature and no specification or requirements document has been referenced or exists in the conversation. Do NOT activate for bug fixes, refactoring, documentation, or tasks where requirements are already clearly defined in the conversation.
Install
npx skills add boxabirds/spec-coach --skill spec-coachgit clone --depth 1 https://github.com/boxabirds/spec-coach.git /tmp/spec-coach
mkdir -p ~/.claude/skills
cp -r /tmp/spec-coach/.claude/skills/spec-coach ~/.claude/skills/spec-coachPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Spec Coach You are a specification coaching assistant. You operate in two modes: - **Coaching mode** (default): Ask Socratic questions to help the author find gaps — do not rewrite, score, or prescribe. - **Evaluation mode** (when `$ARGUMENTS` contains `--evaluate`): Score the spec against all six rubric dimensions (1-10 each), with a metacognitive checkpoint before revealing results. ## Coaching History !`bun run .claude/skills/spec-coach/store.ts context-brief 2>/dev/null || echo "NO_COACHING_HISTORY"` Use this history to personalize your coaching. If it shows weak dimensions, prioritize those. If it includes notes from a prior session on the same spec, open with follow-up on those commitments. If the history command fails or returns NO_COACHING_HISTORY, proceed without history — do not mention it to the user. ## Context Detection !`ls -d .speckit/ .kiro/specs/ .ceetrix/ 2>/dev/null || echo "NO_SPEC_TOOLS_DETECTED"` !`find . -maxdepth 3 -name "*.spec.md" -o -name "*.requirements.md" 2>/dev/null | head -5 || echo "NO_SPEC_FILES_FOUND"` ## Your Task $ARGUMENTS If the user provided a file path, read it. If not, work with whatever requirements context is in the conversation. If there is no spec and no requirements context, help the user establish requirements before building. ## Tool Context Detection Based on the project structure detected above:
Details
- Skill name
spec-coach- Repository
- boxabirds/spec-coach
- Path
.claude/skills/spec-coach/SKILL.md- License
- Apache-2.0
- Repo updated
- 12 March 2026
FAQ
What does the Spec Coach skill do?
Activate when the user is writing, editing, or discussing software requirements, specifications, acceptance criteria, user stories, or feature definitions. Also activate when the user asks to build, implement, or create a feature and no specification or requirements document has been referenced or exists in the conversation. Do NOT activate for bug fixes, refactoring, documentation, or tasks where requirements are already clearly defined in the conversation.
How do I install the Spec Coach skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add boxabirds/spec-coach --skill spec-coach. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Spec Coach popular?
It lives in boxabirds/spec-coach, which has 5 GitHub stars and 0 forks.
Related skills
Detective
10thatmike1/claude-skills
Debugging presented as a case log — titled episodes moving clue -> hypothesis -> ruled-out -> culprit -> fix. Narrative framing over disciplined diagnosis; keeps full technical accuracy. Best for diagnosing bugs and investigations. Use when user invokes /detective, says "detective mode" / "detective style" / "case log". One of a rotating wardrobe with /panels and /punchy.
Criminal Investigation Analyst
5dungnotnull/criminal-investigation-analyst-agent-skill
A professional-support skill for investigators, criminology students, and true-crime researchers that helps organize case facts, generate multiple investigative hypotheses, apply offender-behavior frameworks (MO vs. signature), support geographic pattern reasoning, flag cognitive biases, draft structured interview question sets using cognitive-interview research, and summarize evidentiary strength per hypothesis. Use this skill whenever the user requests case organization, hypothesis generation, behavioral analysis, geographic profiling, bias detection, interview preparation, timeline analysis
Vincent Trading Engine for Agents
5HeyVincent-ai/agent-skills
Strategy-driven automated trading for Polymarket and HyperLiquid. Use this skill when users want to create trading strategies, set stop-loss/take-profit/trailing stop rules, or manage automated trading. Triggers on "trading strategy", "stop loss", "take profit", "trailing stop", "automated trading", "trading engine", "trade rules", "strategy monitor".
Chargily Pay Integration
5bighadj22/ChargilyPay-skill
Integrate Chargily Pay V2 (Algerian payment gateway — EDAHABIA, CIB, and Chargily App) into any store, SaaS, marketplace, or web/mobile app. Use this skill WHENEVER the user wants to accept online payments in Algeria, add a checkout or "pay" button, collect money from customers, sell products or subscriptions, generate payment links, or wire up Chargily — even if they only say "add payments to my store", "accept EDAHABIA/CIB", "Chargily", "Chargily Pay", "DZD payments", or "Algerian payment gateway" without naming an endpoint. Also use it for handling payment webhooks (confirming a paid order,
Cue Financial Deep Read
8sensedeal/cue-skills
用 Cue 跑「财报深读」场景的深度研究:多源公开数据交叉、结论带来源。 Run Cue deep research for the "Financial Deep Read" scenario. 触发 Triggers: 财报深读、财务与业绩、信披与监管 / financial deep read, footnote risk scan, audit opinion
Revolut X Orders
9revolut-engineering/revolut-agent-skills
Revolut X order management — place market or limit orders, view active and historical orders, and cancel orders. Use when the user asks to buy or sell crypto, place a market or limit order, check open orders, cancel an order, or anything related to trading on Revolut X.
Browse the most popular Claude skills, all finance & crypto skills, or write your own with the skills generator.