lore

SpecStory Lore - mine your SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more) into a persistent corpus, surface your reproducible workflows with corroborated evidence, and interactively forge the chosen ones into skills installed across all your agent harnesses. Use when the user wants to turn past AI coding sessions into reusable skills, asks "what could I make into a skill", "mine my lore", "forge skills from my history", or points at a .specstory/history directory.

Quality

83%

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

77%

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

A highly actionable, clearly sequenced skill body with strong verification feedback loops and real one-level-deep engine references. Its weaknesses are length/redundancy (LAWs and failure-mode anecdotes restated) and a monolithic inline orchestration manual that has no separate reference files.

Suggestions

Tighten the redundant LAW restatements: state each LAW once in the OUTPUT CONTRACT and reference it from Step 3 and the hook note rather than re-explaining it; condense the three dated failure-mode anecdotes into a compact table.

Split the bulk of the inline orchestration manual into reference files (e.g. references/laws.md, references/curation.md) so SKILL.md reads as an overview pointing to detailed materials, keeping only the step skeleton and key commands inline.

Dimension	Reasoning	Score
Conciseness	The body does not pad with concepts Claude already knows (no score-1 basis), but at 545 lines it repeats the LAWs across the OUTPUT CONTRACT, Step 3, and the hook-enforcement note, and carries three dated narrative 'Named failure mode #1/#2/#3' anecdotes that could be tightened.	2 / 3
Actionability	Abundant concrete, copy-paste-ready commands ('node "<skill-dir>/scripts/mine-skills.mjs" index --dir ...', 'dossier render', 'forged add --name ...', 'plan render --file ...') with specific flags throughout.	3 / 3
Workflow Clarity	A clear numbered sequence (Step 0 through 6) with explicit validation checkpoints (Step 2b truth-check, dossier fingerprint cache matching, registry consult before proposing, privacy scrub) and feedback loops for the destructive/batch operations (reset, forge).	3 / 3
Progressive Disclosure	The engine logic is appropriately split into scripts/ and lib/ with one-level-deep, well-signaled references, but the orchestration contract itself is a monolithic 545-line inline manual with no reference markdown files (references/ and assets/ are empty), so content that could be separate remains inline.	2 / 3
	Total	10 / 12 Passed

Description

90%

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

A strong, specific, well-triggered description that clearly states both what the skill does and when to use it, with a distinctive niche. The only issue is voice: it addresses the user in second person ('your') rather than the required third person.

Suggestions

Rewrite in third person ('Mines the user's SpecStory coding histories...', 'surfaces reproducible workflows...', 'forges the chosen ones into skills...') instead of second person ('mine your', 'your reproducible workflows').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('mine your SpecStory coding histories... into a persistent corpus', 'surface your reproducible workflows with corroborated evidence', 'interactively forge the chosen ones into skills installed across all your agent harnesses'), which is anchor-3 work, but the voice is second person ('mine your', 'your reproducible workflows', 'all your agent harnesses'), so the rubric's voice penalty reduces specificity by one.	2 / 3
Completeness	Explicitly answers both what (mine/surface/forge) and when ('Use when the user wants to turn past AI coding sessions into reusable skills, asks...'), with explicit triggers.	3 / 3
Trigger Term Quality	Natural phrases a user would actually say are well covered: 'what could I make into a skill', 'mine my lore', 'forge skills from my history', and the '.specstory/history directory' pointer.	3 / 3
Distinctiveness Conflict Risk	A clear, narrow niche ('SpecStory', 'mine my lore', '.specstory/history directory') with distinct triggers unlikely to fire for an unrelated skill.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (546 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: specstoryai/getspecstory
Path: lore/SKILL.md
Commit: c3e0a17

Reviewed: 3 days 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.