Install
$ agentstack add skill-konh-claudetools-specify ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Capture feature intent and acceptance criteria before planning begins. Writes docs/specs/_/spec.md and stops — the user must approve the spec before the plan skill runs.
Doc paths
Default convention: specs live under docs/specs/. Check the project's CLAUDE.md for an overriding location (e.g. a "Docs Layout" section or explicit mention of spec paths) before falling back to the default.
Spec Identifier Derivation
- Use
Globwith patterndocs/specs/*/*.mdto list existing spec folders — do NOT use a trailing-slash pattern (docs/specs/*/) or a baredocs/specs/*, both silently return nothing on Windows; the nested*/*.mdform matches files one level down and works - Generate the current local timestamp as
YY_MM_DD_HH(for example,26_07_18_14) - Combine it with a short kebab-case feature name:
_ - Do not derive or assign a numeric index
Orchestration
Spawn an architect sub-agent (general-purpose) briefed with:
- The user's feature description
- Relevant project rules from
CLAUDE.mdand any project rules directory - The output path:
docs/specs/_/spec.md - The spec format below
The architect writes the spec file directly. You (orchestrator) then:
- Present the spec contents to the user
- Collect feedback and re-brief the architect if changes are needed (iterate until the user approves)
- Stop. Do not run the
planskill or write any code. The user must explicitly request the next step.
Spec Format
# Spec:
## Feature Intent
As a , I want , so that .
## Acceptance Criteria
- **Given** **When** **Then**
- (one bullet per observable behaviour; cover the happy path and the most important edge cases)
## Out of Scope
- (explicit exclusions — things the feature deliberately will not do)
## Ambiguities
- [NEEDS CLARIFICATION: ]
- (omit this section entirely if there are no ambiguities)
Rules
- Do NOT write any plan, code, or assets — only the spec document.
- Use
[NEEDS CLARIFICATION: …]markers freely — surfacing unknowns early is the point. - The spec folder name starts with its creation timestamp and uses a kebab-case name:
docs/specs/26_07_18_14_my-feature/spec.md. - Do not create
plan.mdin the spec folder — that is theplanskill's job.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: KonH
- Source: KonH/ClaudeTools
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.