spike-wrap-up

Package findings from a completed spike into a durable, project-local skill that auto-loads on future similar work. Reads the most recent `.gsd/workflows/spikes/` directory, interviews the user briefly on what's reusable, then writes `.claude/skills/<name>/SKILL.md`. Use when asked to "wrap up the spike", "package this as a skill", "make this reusable", "turn findings into a skill", or at the end of the synthesize phase of `/gsd start spike`. Closes the parity gap with GSD v1's `/gsd-spike-wrap-up`.

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured, actionable, and concise, with a clear multi-step workflow that includes decision branches and guardrails plus an observable success checklist. Progression is appropriately organized across tagged sections with only shallow external references.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding of concepts Claude already knows; every XML-tagged section (objective, core_principle, anti_patterns) adds project-specific guidance that earns its tokens.	3 / 3
Actionability	Provides concrete, executable guidance — exact paths (.gsd/workflows/spikes/, .claude/skills/<name>/), named files (SCOPE.md, RECOMMENDATION.md), a full SKILL.md template, and a literal .gsd/DECISIONS.md line format to copy.	3 / 3
Workflow Clarity	A clearly sequenced 6-step process with explicit decision branches (Step 2 "if not worth it, stop") and guardrails (Step 5 "Do NOT delete the spike"), capped by an observable success_criteria checklist.	3 / 3
Progressive Disclosure	Content is cleanly split into well-signaled XML-tagged sections with no nested-reference wall; with no bundle files present, the single-level repo path references keep navigation shallow and the overview lean.	3 / 3
	Total	12 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: it states concrete actions, provides natural trigger phrasings a user would say, and explicitly covers both what the skill does and when to invoke it. Its narrow GSD-specific scope keeps conflict risk low.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "Package findings", "Reads the most recent .gsd/workflows/spikes/ directory", "interviews the user briefly", "writes .claude/skills/<name>/SKILL.md" — rather than vague language.	3 / 3
Completeness	Explicitly answers both what it does (package, read, interview, write the SKILL.md) and when to use it ("Use when asked to 'wrap up the spike'... or at the end of the synthesize phase").	3 / 3
Trigger Term Quality	Covers natural phrases a user would actually say — "wrap up the spike", "package this as a skill", "make this reusable", "turn findings into a skill" — plus the specific /gsd start spike synthesize-phase entry point.	3 / 3
Distinctiveness Conflict Risk	Occupies a narrow, distinctive niche (spike wrap-up within the GSD workflow) with trigger phrases unlikely to fire for unrelated skills, minimizing conflict risk.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: gsd-build/gsd-2
Path: src/resources/skills/spike-wrap-up/SKILL.md
Commit: 33c00aa

Reviewed: about 13 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.