helderberto/check
skills/check/SKILL.md
Verify implementation against plan. Shows progress and finds blockers. Use after implementing a plan.
$ install --global
skillsauthnpx skillsauth add helderberto/skills checkInstall 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: May 12, 2026, 2:53 AM115.4s1 file scanned
SKILL.md
- name:
- check
- description:
- Verify implementation against plan. Shows progress and finds blockers. Use after implementing a plan.
- argument-hint:
- [slug]
Check Implementation
Verify plan checkboxes against the codebase. Unmark items that don't hold up ([x] → [ ]).
Interactive prompts: present options as a numbered list and wait for the user's choice.
Input
The argument (if provided) is: $ARGUMENTS
Use the argument as <slug> if given. Accepts slug or @file reference.
If no argument is provided, list available plans as numbered options and wait for the user's choice.
Progress Algorithm
Count - [x] and - [ ] lines under each ## Phase N heading. Per-phase: Phase N — title: checked/total. Sum → Total: checked/total.
Workflow
1. Load the plan
Read .specs/plans/<slug>.md. If missing, list plans as numbered options and wait for the user's choice.
2. Fast-path: check if implementation exists
If primary module file(s) from Phase 1 don't exist, skip subagent — report 0/N — not yet started, list Phase 1 done-when items.
3. Launch read-only review
Use a general-purpose subagent (not code-review). The subagent must be read-only (no file writes, no edits). It should:
- Read every section of the plan — architectural decisions, each phase, done-when checkboxes
- For each phase, check every
- [ ]/- [x]item against the codebase - Run the project's test suite and include pass/fail results
- For each checkbox, determine whether it should be checked (
[x]) or unchecked ([ ])
Collect findings into two categories:
- BLOCKERS — checked items that don't hold up, failing tests, broken contracts
- SUGGESTIONS — improvements, minor gaps, style issues
4. Update checkboxes
Using the subagent's report, update each checkbox in .specs/plans/<slug>.md:
- Items that pass verification →
[x] - Items that fail verification →
[ ](unmark)
5. Report
Count progress per phase (Progress Algorithm), then print:
## Verification: <slug>
### Progress
Phase 1 — title: checked/total
> Phase 2 — title: checked/total
Total: checked/total
The > marks the first incomplete phase (cursor).
### BLOCKERS
- (list or "None")
### SUGGESTIONS
- (list or "None")
If all items verified (total checked = total):
All phases complete — implementation verified.
6. Next steps
If blockers exist, list items to fix, then re-run /hb:check <slug>.
If all items verified, suggest creating a PR or shipping.
Rules
- The review subagent must be read-only — it must not create, edit, or delete any files
- The only file writes this skill makes are: checkbox updates in the plan
- Never modify implementation code — only observe and report
Related Skills
helderberto/teach
tools
VerifiedTrustedCommunity
Teach the user a new skill or concept, within this workspace.
10SKILL.mdUpdated Jun 13, 2026
helderberto/handoff
documentation
VerifiedTrustedCommunity
Compact the current conversation into a handoff document for another agent to pick up.
10SKILL.mdUpdated May 20, 2026
helderberto/caveman
testing
VerifiedTrustedCommunity
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
10SKILL.mdUpdated May 12, 2026
helderberto/create-skill
development
VerifiedTrustedCommunity
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill, or asks "make a skill for X".
8SKILL.mdUpdated May 20, 2026