jaisonerick/verify-symbol
plugins/spec-plugin/skills/verify-symbol/SKILL.md
Confirm whether a code symbol (method/class/field/endpoint/flag) actually exists and return its REAL signature + definition location — or the nearest match. Uses LSP/introspection, never grep-spelunking. Cheap and fast.
development
Updated Jun 8, 2026
$ install --global
skillsauthnpx skillsauth add jaisonerick/spec-plugin verify-symbolInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 8, 2026, 6:10 AM12.1s1 file scanned
SKILL.md
- name:
- verify-symbol
- description:
- Confirm whether a code symbol (method/class/field/endpoint/flag) actually exists and return its REAL signature + definition location — or the nearest match. Uses LSP/introspection, never grep-spelunking. Cheap and fast.
- argument-hint:
- [symbol + repo, e.g. 'Partner#kyc_pending? in <repo>']
- allowed-tools:
- Read, Glob, Grep, Bash
- context:
- fork
- agent:
- Explore
- effort:
- low
Run this when you need to answer one question precisely and cheaply: does this symbol exist, what is its real signature, and where is it defined? (Or, if it doesn't: what's the nearest real thing?) This is the antidote to code that assumes partner.slug or CreditOffer.find_by_offer and turns out to be wrong.
This skill runs in an isolated forked Explore child and returns only its tight conclusion — so the caller's context stays clean.
Never grep-spelunk to answer this. Use the language's own runtime/compiler, an LSP, or a structural tool — they give ground truth.
Procedure
- Detect the project language of the target symbol (file extension / project markers).
- Load only that language's toolkit card — locate and read it (don't load other languages):
Read that file (find ~/.claude/plugins -type f -path '*spec-plugin/references/<lang>.md' 2>/dev/null | head -1ruby.md/typescript.md/python.md). It has the exact verify/navigate commands for the language. If no card matches, fall back toast-grep/ctagsfromreferences/toolkit.md. - Run the card's "Navigate — verify a symbol" commands for the target. Prefer native LSP (if the language has an LSP plugin) → runtime/compiler introspection → ast-grep → ctags.
- If it doesn't exist, find the nearest real match (closest method/field/endpoint that probably was meant) and its location.
Tool versions resolve via asdf automatically — call ruby/node/python directly.
Output
SYMBOL: <name>
EXISTS: yes | no
SIGNATURE: <real signature>
DEFINED AT: <file:line> (or "—")
NEAREST MATCH: <only if EXISTS=no — the real thing probably meant, with location>
HOW CHECKED: <one line: LSP / ruby source_location / TS LanguageService / ast-grep / …>
Do not modify code. Do not over-explain. If you can't resolve it (missing deps, won't boot), say exactly what's blocking so the caller can fix it.
Related Skills
jaisonerick/assess-effectiveness
tools
VerifiedTrustedCommunity
Assess how the LATEST spec-plugin version is performing across every previous session that invoked it — aggregate run efficiency (thinking%, compactions, exploration-vs-skills, preload firing, fresh-per-story), process adherence, and recurring spec-quality issues — then propose concrete, evidence-backed improvements for the NEXT version (plugin skills/agents/hooks, and spec/process patterns). Read-only: proposes, never self-modifies. Not tied to a single run.
SKILL.mdUpdated Jun 9, 2026
jaisonerick/trace-flow
development
VerifiedTrustedCommunity
Walk one value or action end-to-end across every layer/hop — go-to-definition by go-to-definition, or with a debugger breakpoint — and report the real state transitions and where the contract/shape diverges. The workhorse for architecture sketches and cross-layer debugging.
SKILL.mdUpdated Jun 7, 2026
jaisonerick/setup-env
testing
VerifiedTrustedCommunity
Bring a fresh worktree/checkout to a runnable state — verify base HEAD, copy gitignored files (.env), allocate per-agent DB/test env, install deps, run the smoke gate. Deterministic, mechanical. Reports a single ready/blocked verdict.
SKILL.mdUpdated Jun 7, 2026
jaisonerick/probe-contract
development
VerifiedTrustedCommunity
Find out how code ACTUALLY behaves by executing the real classes in a REPL — the real request/response shape, the real return value — without relying on a live staging environment. Beats writing a test for 'how does this behave?'.
SKILL.mdUpdated Jun 7, 2026