forward-spec
Skill0 starsChanged 4 months agoNo licenceView on GitHub
Use this skill when the user asks for a forward-looking design spec, research plan, proposal, RFC, optimization plan, "what should we do about X", "audit the codebase for Y and propose a plan", or any artifact where the goal is evidence-led recommendations organized for implementation — not a recap of past work. Optionally spawns parallel research agents up front, optionally pressure-tests the draft through `/codex-pair` until GO, and emits a single markdown document with executive summary, audit sections, rollout-tiered opportunities, mermaid diagrams (portable subset), and a reviewer traceability table. Counterpart to `audit-trail` (backward-looking). Triggers: "design spec", "research plan", "forward spec", "RFC", "proposal", "investigate and propose", "audit X and recommend", "what should we change", "optimization plan", "rollout plan".
In this repository7 other files it gives its agents.
- adversarialSkill
- audit-trailSkill
- codex-pairSkill
- explainerSkill
- remarkable-htmlSkill
- remarkable-mdSkill
- roadmap-digestSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
45 rules. About 0 are common, 21 are distinctive, and 24 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈21
Distinctive · estimate
This author's own choices. Worth a look.
24
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
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.