skills/requirements/requirement-summary/SKILL.md
Alias for requirement-summarizer. Produces a structured summary of a requirements document — the key obligations, grouped by actor and concern, with the MUST/SHOULD/MAY breakdown. Use when onboarding to a large spec, when deciding what to implement first, or when the user asks what a standard actually requires.
npx skillsauth add santosomar/general-secure-coding-agent-skills requirement-summaryInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill is an alias. → requirement-summarizer for the full workflow.
The two names exist because "summary" (the noun — the artifact you want) and "summarizer" (the verb — the thing that produces it) both get asked for. They mean the same thing. Follow the link.
What the target skill does:
| Input | Output | | ------------------------ | -------------------------------------------------------- | | Requirements document | Obligations table: actor → MUST / SHOULD / MAY | | RFC / standard | Normative statements extracted, informative prose stripped | | Long spec | Grouped by concern (auth, storage, transport, …) |
| You actually wanted… | Go to |
| ---------------------------------------------------------- | ------------------------------------- |
| To compare two versions of requirements | → requirement-comparison-reporter |
| To check if code covers requirements | → requirement-coverage-checker |
| To make one vague requirement precise | → requirement-enhancer |
| To turn a requirement into concrete test scenarios | → scenario-generator |
Otherwise: → requirement-summarizer.
development
Extracts human-readable pseudocode from a verified formal artifact (Dafny, Lean, TLA+) while preserving the verified properties as annotations, so the proof-carrying logic can be reimplemented in a production language. Use when porting verified code to an unverified target, when documenting what a formal spec actually does, or when handing a verified algorithm to an implementer.
development
Translates natural-language or pseudocode descriptions of concurrent and distributed systems into TLA+ specifications ready for the TLC model checker. Identifies state variables, actions, type invariants, safety properties, and liveness properties from the description. Use when formalizing a protocol, when the user describes a distributed algorithm to verify, when designing a consensus or locking scheme, or when starting formal verification of a concurrent system.
testing
Reduces a TLA+ model so TLC can actually check it — shrinks constants, adds state constraints, abstracts data, or applies symmetry — when the state space is too large to enumerate. Use when TLC runs out of memory, when checking takes hours, or when a spec works at N=2 and you need confidence at larger scale.
development
TLA+-specific instance of model-guided repair — reads a TLC error trace, identifies the enabling condition that should have been false, strengthens the corresponding action, and maps the fix to source code. Use when TLC reports an invariant violation or deadlock and you have the code-to-TLA+ mapping from extraction.