specstoryai/getspecstory / lore
lore
FlaggedSpecStory 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.
AGENTS.md
View on GitHub# Agent Rules for the Lore Repo
You are working ON the lore engine/skill, not running it. Read [CONTRIBUTING.md](CONTRIBUTING.md)
first; these are the rules that bite:
- **Zero dependencies, ever.** Plain Node only (`node:sqlite`, `node:fs`, `node:crypto`). If a
change seems to need an npm package, stop and ask.
- **The engine is deterministic; the agent judges.** Parsing/counting/fingerprinting/rendering live
in `scripts/` and must be byte-reproducible. Judgment (naming, themes, verification) belongs in
SKILL.md's contract or the workflow scripts.
- **Fixtures are the spec.** Every parsing or rendering claim needs a fixture
(should-flag/should-pass style). New provider formats use REAL bytes verified against
specstory-cli's writers - never invented. Parser behavior changes bump `PARSER_VERSION` in
`scripts/lib/db.mjs`.
- **The golden file is intentional.** If `fixtures/golden/forge-plan.md` fails, either your change
is wrong or the layout change is deliberate - regenerate with `UPDATE_GOLDEN=1 npm test` and say
so in the commit body.
- **Never weaken the output contract.** PASS-THROUGH markers, sentinels, and the named failure
modes in SKILL.md are enforcement and institutional memory; do not soften or delete them.
- **No em dashes** anywhere - docs, comments, or engine-emitted strings. Use " - ".
- **Run `npm test` after every change** (29+ tests; Node >= 22.5). Conventional commits with a
why-body: `type(scope): subject`.
- Use a scratch corpus while developing: `--db /tmp/dev-lore.db`. Never write to the user's real
`~/.specstory/lore.db` from tests or experiments.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |