.claude/skills/pair-capability-estimate/SKILL.md
Estimates a refined user story using the adopted estimation methodology. Reads estimation framework from guidelines and methodology from way-of-working. Idempotent: detects existing estimate, confirms rather than re-estimating. Invocable independently or composed by /pair-process-refine-story.
npx skillsauth add foomakers/pair pair-capability-estimateInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Apply the adopted estimation methodology to size a refined user story. Reads the estimation framework from guidelines and the adopted methodology from way-of-working.
| Argument | Required | Description |
| -------- | -------- | ------------------------------------------------------------------------------------------------- |
| $story | Yes | Story ID to estimate. The story must be in Refined state with acceptance criteria. |
| $method| No | Override estimation method: complexity, time, ai-assisted, forecast, hybrid. If omitted, uses the adopted methodology from way-of-working. |
Check: Does the story already have an estimate (story points, hours, or sizing label)?
Skip: If no existing estimate, proceed to Step 3.
Act: Present the existing estimate:
Story #
$storyalready estimated: [estimate value] ([method used]). Re-estimate? (Only if explicitly requested by developer.)
Verify: If developer confirms current estimate → exit. If developer requests re-estimation → proceed to Step 3.
$method provided?complexity → complexity-based-estimation.mdtime → time-based-estimation.mdai-assisted → ai-assisted-estimation.mdforecast → forecast-based-estimation.mdhybrid → hybrid-estimation.mdAct: Analyze the story using the selected method:
Act: Present the estimate to the developer:
Estimation for #
$story:| Factor | Assessment | |--------|-----------| | Method | [method name] | | Estimate | [value + unit] | | Confidence | [High/Medium/Low — reason] | | Key Factors | [complexity drivers, risks, unknowns] |
Accept this estimate?
Verify: Developer approves. If developer disagrees → discuss and adjust.
ESTIMATION COMPLETE:
├── Story: [#ID: Title]
├── Method: [complexity | time | ai-assisted | forecast | hybrid]
├── Estimate: [value + unit (e.g., 5 SP, 20h, M(3))]
├── Confidence: [High | Medium | Low]
├── Rationale: [key factors]
└── Status: [Recorded | Confirmed existing]
When composed by /pair-process-refine-story:
/pair-process-refine-story may invoke /pair-capability-estimate after AC and technical analysis are complete./pair-process-refine-story includes the estimate in the story sizing section.When invoked independently:
/pair-capability-record-decision.development
Creates or updates a Product Requirements Document through structured template analysis, hypothesis-driven information gathering, and iterative review. Idempotent — detects existing PRD and offers selective section update.
development
Reviews a pull request through a structured 6-phase process: validation, technical review, adoption compliance, completeness check, decision, and optional merge with parent cascade. Composes /verify-quality, /verify-done, /record-decision, /assess-debt (required) and /verify-adoption, /assess-stack (optional with graceful degradation). Output follows the code review template. Idempotent — re-invocation resumes from incomplete phases.
tools
Refines a user story from Todo to Refined state through structured phases: selection, requirements analysis (Given-When-Then), technical analysis, sprint readiness, and documentation. Section-level idempotency — detects partial refinement and resumes. Composes /write-issue for PM tool updates.
testing
Breaks a refined user story into implementation tasks. Task-level idempotency: detects existing tasks and creates only missing ones. Appends condensed Technical Analysis + Task Breakdown (checklist, Dependency Graph, AC Coverage table, detailed tasks) to the story body. Composes /write-issue to update the story issue body. Tasks are documented inline in the story — no separate task issues are created.