--- name: scale-capability-match description: Maps a friction point to the AI capability chain it needs (classification, summarization, generation, extraction, search and retrieval, orchestration), sets the OAR level, runs the 4 Ps, and checks readiness. Use when the user says "what kind of AI do we need", "match capabilities", "which AI category", "are we ready for this", or after scale-ai-gate returns AI candidate. --- # scale-capability-match Write the Capability section of `artifacts/scale-capability-decision.md`. You don't buy a tool. You buy a capability chain aimed at an outcome. ## Preflight (every run) 1. Confirm `GTM-AI-OS/` is accessible. If not: "I need access to your GTM-AI-OS folder. Select it in Cowork's folder picker, or run `os-install` from the core plugin." Stop until it is. 2. Read `CLAUDE.md`, `INDEX.md`, and the last 20 lines of `signals/log.md`. 3. Check the prerequisites below. For anything missing, ask the cold-start questions and offer: (a) run the earlier skill now, or (b) fast path: answer the questions and this skill writes a minimal version of the missing artifact marked `status: draft (fast path)`. 4. On finish, update the artifact row in `INDEX.md` and append one line to `signals/log.md`: ` | | | | `. ## Prerequisites - Gate verdict = AI candidate in `artifacts/scale-capability-decision.md`. - `artifacts/scale-friction-map.md` and `artifacts/scale-five-whys.md`. Cold-start: "Paste the friction point and its root cause in two sentences." Continue with those marked fast path. ## Step 1: Name the chain For the friction point, select the capabilities needed and put them in execution order. Use `references/capability-map.md` for the pain → capability patterns. Example: slow QBR prep = search and retrieval → extraction → summarization → generation. ## Step 2: OAR level Optimize (time back), Amplify (revenue-linked, proactive), Reinvent (changes the model). Recommend the lowest level that solves the friction. Most teams haven't finished Optimize; say that if relevant. ## Step 3: Human in the loop Classify the work: pothole (repetitive, low risk: more AI), road (repeatable process: mixed), bridge (complex, high stakes: more human). Outbound to prospects is a road with brand risk, never a pothole. ## Step 4: The 4 Ps Score 1 to 5: Possibilities (how big is the outcome it could enable), Probability (how likely it works here), Payoff (dollar impact from the friction map), Perspiration (adoption effort the team owes). High payoff with high perspiration is a warning, not a plan. ## Step 5: Readiness Score 1 to 5: data (from `scale-data-inventory`), integration, governance, feedback loop. Any 1 or 2 becomes a prerequisite listed in the decision. ## Step 6: Expected outcome Write the sentence: "If we deploy at on , we expect to move from to in ." ## Step 7: Write Fill the Capability section. Update `INDEX.md`. ## Hand off Say: "Now decide how to get the capability. Run `scale-vendor-scorecard`."