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.
fixtures/golden/forge-plan.md
View on GitHub<!-- PASS-THROUGH FORGE PLAN: present this document VERBATIM as the plan body (SKILL.md LAW 1, failure mode #3). -->
# ⚒ Forge plan · projA lore
📜 13 sessions · 29 beats · 2 candidates proposed
## Proposed (2)
---
### 1 · verify-build
**high confidence** · verifier: confirmed · from `build:run × go build ▸ go test`
> **Use when:** Use when the user asks to run a build and the tests before declaring work done.
**Needs first:**
- A Go workspace with tests
**The method:**
1. Run go build ./... and stop on any compile error
2. Run go test ./... and read every failure before touching code
**Done when:**
- Both commands exit 0 in the same beat
**When it goes wrong:**
- ⚠ Tests fail after a green build
↳ Read the first failing test before editing anything (`projA/.specstory/history/2026-05-02_11-00-00Z-can-we-run-a.md:30`)
---
### 2 · locate-before-touching
**latent practice** · 3 beats · evidence unchanged
**Locate the mechanism before touching it**
Pins the implementation site read-only, restates the observed behavior, and only then authorizes an edit that mirrors the located pattern.
*Miner's note: lens=diagnosis-style | the user experiences this as just asking questions*
**In their own words:**
> "Show me where in the code we are doing this. Don't write any code yet, just locate the mechanism."
> (`cccc-cccc-cccc-cccc/2026-05-10_09-00-00Z-where-is-save-implemented.md#1`)
---
## Skipping (1)
- **xcodebuild ▸ xcodebuild**: generic build loop, no judgment encoded
---
## On approval
1. Forge each skill to personal scope (~/.agents/skills/<name>)
2. Symlink into every harness skills dir
3. Register each with `forged add`; record a `forged decline` for every skip
=== dossiers above: 2 ===
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 |