discovery
Skill14 starsChanged 36 days agoApache-2.0View on GitHub
Populate and refresh `.apex` hub docs (glossary, surface standards, cross-surface conventions) from the real codebase via a seeded, per-item confirmed interview. Re-runnable — a second run surfaces only new or drifted items.
26 other projects use a version of this.
Adopted by
Most recently taken up by
- GustavoAlecio/claude-setuptheir own version, first seen Nov 8, 2026
- anotb/forward-deployedtheir own version, first seen Nov 8, 2026
- newkirkjosh/skillstheir own version, first seen Nov 1, 2026
- jantichy/claudetheir own version, first seen Oct 27, 2026
- CrowdStrike/agentworks-skillstheir own version, first seen Oct 25, 2026
- steepy-it/steepy-formulatheir own version, first seen Oct 25, 2026
Used with
Projects with it also use specify and architecture.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
ArvorCoSkillspecify
Create feature specification from natural language description. Use when starting a new feature or creating a spec. Triggers on: create spec, specify feature, new feature spec.
Also in 3 projects that use this
AnthropicSkillarchitecture
Create or evaluate an architecture decision record (ADR). Use when choosing between technologies (e.g., Kafka vs SQS), documenting a design decision with trade-offs and consequences, reviewing a system design proposal, or designing a new component from requirements and constraints.
Also in 3 projects that use this
Other versions26 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 26
- AICMO/AiCMO-Marketing-Prompt-Collection★ 229same name
- avelikiy/great_cto★ 112same name
- joelhooks/joelclaw★ 65same name
- Kanevry/session-orchestrator★ 53same name
- jantichy/claude★ 45same name
- DGouron/review-flow★ 42same name
- Dan-Cleary/fdestack★ 40same name
- tekliner/improvado-agentic-frameworks-and-skills★ 17same name
- intent-driven-dev/skills★ 9same name
- steepy-it/steepy-formula★ 5same name
16 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- templates/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- steepy-apex-bootstrapSkill
- steepy-apex-bootstrapSkill
- brainstormSkill
- checkSkill
- implementSkill
- inceptionSkill
- initSkill
- loop-engineerSkill
- new-surfaceSkill
- planSkill
- reviewSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 24 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 32
Only this SKILL.md is meant to stay in context for the whole run.
- Very specific: line 39
Always set model: explicitly when dispatching the Explore subagent in Step 2.2 and the inception explorer in Step 2a.2 — an omitted model …
- Very specific: line 45
Never hardcode a concrete model id in explore-surface-prompt.md or explore-inception-prompt.md.
“Common” is measured: kept by at least 6 in 10 of the 24 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
discovery
Populate and refresh the hub's prose docs — glossary.md, each surface standard (the single
standards/<surface>.md file or the modular standards/<surface>/ folder), and conventions.md —
from the actual codebase, via a seeded interview the user confirms item by item.
discovery is a standalone hub-aware skill, like init / new-surface / check — it is not
part of the brainstorm → plan → implement → review chain. It has its own precondition step (Step 0) and
does not follow the chain skills' shared gear-selection or Model-Selection-lock format.
Engine root: this skill's base directory is
<engine-root>/skills/discovery/; engine scripts live two levels up, at<engine-root>/scripts/. Resolve them relative to the base directory your harness reports for this skill.
Procedure
The steps live in co-located files, each read in full at the point named here:
| Steps | File | Read it |
| 0–1: preconditions, run scoping | entry.md | at the start of every run |
| 2: per-surface iterative loop | surface-loop.md | before the first surface or the inception source (Step 2a reuses its Steps 2.4–2.5) |
| 2a: inception source, only after a complete inception run | inception-source.md | when Step 1 scopes an inception source |
| 3–4: coherence gate, report | finish.md | after the last surface or source |
Only this SKILL.md is meant to stay in context for the whole run; a context compaction can drop the step files you read earlier. Before you act on a step, its file must be fully in view. If it is not — after a compaction, on resume, or when only a summary of it remains — re-read it from this skill's base directory first. Never act on a summary of a step file.
Model Selection
Always set model: explicitly when dispatching the Explore subagent in Step 2.2 and the inception
explorer in Step 2a.2 — an omitted model inherits the expensive session model and defeats the tier
policy. Floor at standard; rise to most-capable for a large or subtle surface. The inception
explorer runs at standard. Translate the tier to a concrete model by judgment at
dispatch time using your harness's available models; most-capable is the ladder's top rung, not an
open-ended "best available", and a pricier model sitting above it is never reached from a tier.
Never hardcode a concrete model id in explore-surface-prompt.md or explore-inception-prompt.md.
This flow dispatches no reviewer subagent: every write is prose to a stable doc, gated per item by
the human in the Step 2.4 seeded interview (Step 2a.3 for the inception source); validate-hub
(Step 3) is the deterministic net. The Explore subagent dispatched in Step 2.2 and the inception
explorer dispatched in Step 2a.2 are explorers, not reviewers.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.