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

88%

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

81%Weight 40%Scale 1-5

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

A highly actionable, well-sequenced operational skill with concrete commands and strong validation/feedback loops for its destructive batch forging step. Its main weakness is verbosity from dated incident narratives and inlined detail that could be offloaded to reference files.

Suggestions

Condense the three 'Named failure mode' incident narratives (dated 2026-06-09/10) into terse one-line lessons, or move them to a 'Past failures' reference file, to cut padding and remove time-sensitive date/version detail from the main body.

Extract the Step 2 registry recommendation table and the full engine command/flag reference into a separate REFERENCE.md, keeping SKILL.md as an overview that links one level deep.

Tighten the OUTPUT CONTRACT preamble so each LAW opens with its mechanical rule before any rationale, reducing narrative while preserving the sentinel-based checks.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational guidance with no basic-concept padding, but the dated incident narratives ('Named failure mode #1 (2026-06-09, BearClaude run)...', 'Opus 4.8') and lengthy STORY-style LAW preamble add noticeable padding that could be tightened; time-sensitive dates also penalize conciseness here.	3 / 5
Actionability	Fully executable, copy-paste-ready commands throughout ('node "<skill-dir>/scripts/mine-skills.mjs" index --dir <history-dir>', 'report --min-sessions 3 --top 10', 'dossier render', 'forged add', etc.) with specific flags covering the common cases.	5 / 5
Workflow Clarity	A clearly sequenced Step 0–Step 6 pipeline with explicit validation checkpoints (Step 2b truth-check, cache fingerprint compare, registry recommendation check) and feedback loops; destructive/batch forging is gated by plan mode plus a PreToolUse hook, satisfying the destructive-operation validation requirement.	5 / 5
Progressive Disclosure	Good structure with real bundle files (scripts/mine-skills.mjs, deep-mine.workflow.js, theme-sweep.workflow.js, hooks/, lib/) referenced one level deep with clear path-based navigation; minor gap in that substantial operational detail (the registry recommendation table, full command reference) is inlined in SKILL.md rather than split into a reference file.	4 / 5
	Total	17 / 20 Passed

Description

95%Weight 40%Scale 1-5

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 description that clearly states capabilities and gives concrete, natural trigger phrases including a directory pointer. Only marginally below the top specificity anchor due to slightly abstract action objects.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('mine your SpecStory coding histories... 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'), but the verbs act on slightly abstract objects rather than granular operations, leaving minor coverage gaps versus the comprehensive anchor.	4 / 5
Completeness	Explicitly answers both what (mine/surface/forge/install across harnesses) and when (a 'Use when...' clause with concrete trigger phrases), matching the top anchor.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including synonyms and a concrete path: '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.'	5 / 5
Distinctiveness Conflict Risk	A clear niche anchored by SpecStory histories and the .specstory/history directory with distinct triggers ('mine my lore', 'forge skills from my history'), giving minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 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: ec9c70f

Reviewed: 6 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.