radarist/structured-analytic-skills / skills/evolution-stage
evolution-stage
VerifiedTags a named technology, capability or vendor category with its Wardley evolution stage — Genesis, Custom built, Product (+rental) or Commodity (+utility) — anchored in observable evidence, and states the way of working that stage implies. Use when asked "is this a product or still bespoke?", "build vs buy for X", "where are these tools in their lifecycle?" or "what evolution stage is X at?". Not for the whole value chain and its dependencies (use `wardley-map-drafting`) and not for evidence of technical maturity (use `score-technology-readiness`).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 12.0 KB |
| agents/openai.yaml | config | 343 B |
| evals/evals.json | config | 4.3 KB |
| references/placement-signals.md | markdown | 5.6 KB |
evals/evals.json
View on GitHub{
"skill_name": "evolution-stage",
"evals": [
{
"id": 1,
"case_id": "evo-pos-1",
"kind": "positive",
"prompt": "This vendor calls its offering a product, but every customer I've spoken to spent four months tuning it. What evolution stage is it really at, and what does that mean for how we should run the project?",
"expected_output": "A response that satisfies these checks: Places the component in one Wardley evolution stage with a named label; Anchors the placement in observable evidence such as integration time or reference-customer count; States the way of working the stage implies; Flags the mismatch between the vendor's product framing and bespoke integration.",
"files": [],
"expectations": [
"Places the component in one Wardley evolution stage with a named label",
"Anchors the placement in observable evidence such as integration time or reference-customer count",
"States the way of working the stage implies",
"Flags the mismatch between the vendor's product framing and bespoke integration"
],
"skills": [
"evolution-stage"
]
},
{
"id": 2,
"case_id": "evo-pos-2",
"kind": "positive",
"prompt": "Half of these tools are bespoke one-offs and half are off-the-shelf utilities, but our brief compares them all the same way. Tag each technology with where it sits in its lifecycle so the comparison stops being apples to oranges.",
"expected_output": "A response that satisfies these checks: Assigns exactly one evolution stage per named component; Notes that components at different stages need different ways of working; Recommends utility treatment for commodity components and time-boxed experiments for novel ones.",
"files": [],
"expectations": [
"Assigns exactly one evolution stage per named component",
"Notes that components at different stages need different ways of working",
"Recommends utility treatment for commodity components and time-boxed experiments for novel ones"
],
"skills": [
"evolution-stage"
],
"requires_input": true
},
{
"id": 3,
"case_id": "evo-pos-3",
"kind": "positive",
"prompt": "Is this capability genesis, custom built, product or commodity? Give me the Wardley evolution stage with a rationale I can defend to the architecture board.",
"expected_output": "A response that satisfies these checks: Uses the four Wardley stage labels; Gives a one-line rationale citing something countable or checkable; Marks the placement as an estimate when only vendor self-positioning supports it.",
"files": [],
"expectations": [
"Uses the four Wardley stage labels",
"Gives a one-line rationale citing something countable or checkable",
"Marks the placement as an estimate when only vendor self-positioning supports it"
],
"skills": [
"evolution-stage"
]
},
{
"id": 4,
"case_id": "evo-neg-1",
"kind": "negative",
"prompt": "Map our whole value chain from the end-user need down through every supporting component so I can see the dependencies and where to focus.",
"expected_output": "A response that satisfies these checks: Anchors on the user need and lays out a full value chain with dependencies; Does not stop at scoring a single component.",
"files": [],
"expectations": [
"Anchors on the user need and lays out a full value chain with dependencies",
"Does not stop at scoring a single component"
],
"skills": [
"wardley-map-drafting"
]
},
{
"id": 5,
"case_id": "evo-neg-2",
"kind": "negative",
"prompt": "How much deployment evidence exists for this inference accelerator? I need the readiness level with the proof at each level before we commit.",
"expected_output": "A response that satisfies these checks: Assesses maturity against a cumulative evidence-gated readiness scale; Does not assign a build-buy-rent strategic stage.",
"files": [],
"expectations": [
"Assesses maturity against a cumulative evidence-gated readiness scale",
"Does not assign a build-buy-rent strategic stage"
],
"skills": [
"score-technology-readiness"
]
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |