cc-sdd-new-agent

Add or extend coding-agent support in cc-sdd by executing the SOP in docs/cc-sdd/sop-new-agent.md end-to-end. Use when introducing a new agent, adding a subagent-capable variant, or evaluating migration of an existing supported agent to skills-based templates.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

93%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-engineered instruction skill: exact paths, runnable verification commands, an approval gate before implementation, and clean deferral of detail to real one-level-deep reference files. Minor room to tighten repeated statements of the plan path and scope inputs, and to add an explicit fix-and-re-verify loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and imperative with no concept over-explanation, but the plan deliverable path and the scope/work-type inputs are each restated two to three times (Default Operation Mode, Create Plan Document, Completion Criteria), which could be trimmed. Anchor 5 requires every token to earn its place; this repetition keeps it at anchor 4.	4 / 5
Actionability	Guidance is fully executable throughout: exact file paths (tools/cc-sdd/src/agents/registry.ts, templates/manifests/{agent-id}.json, test/realManifest{AgentName}.test.ts) and copy-paste-ready commands (npm test, npm run build && node dist/index.js --agent {agent-id} --dry-run, --overwrite=force, --lang ja). Concrete input collection and per-scope base-template choices cover the common cases.	5 / 5
Workflow Clarity	The sequence is clear (collect inputs, Phase 1 research, plan, approval gate, implement, migration handling, verify) with explicit checkpoints such as 'Start implementation only after the plan file exists and the user has confirmed' and 'If tests cannot run, explicitly report which step is blocked'. It falls short of anchor 5 because there is no explicit fix-and-re-run feedback loop when verification fails.	4 / 5
Progressive Disclosure	The body works as an overview with a clearly signaled References section pointing to two real, one-level-deep bundle files (references/skills-migration.md, references/plan-output-checklist.md), verified to exist, while SOP and template detail is deferred to repo docs. Navigation is easy and content is appropriately split.	5 / 5
	Total	18 / 20 Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with an explicit and well-structured 'Use when' trigger clause and clear niche anchoring to cc-sdd. Its only weakness is that the capability statement stays at a high level, delegating concrete actions to the referenced SOP rather than naming several specific capabilities itself.

Dimension	Reasoning	Score
Specificity	Names the domain ('Add or extend coding-agent support in cc-sdd') and concrete actions ('executing the SOP in docs/cc-sdd/sop-new-agent.md end-to-end'), but only 1-2 capability-level actions are stated, with the bulk deferred to the SOP document. It does not reach anchor 4, which expects several distinct specific actions listed.	3 / 5
Completeness	Both halves are explicit: the what ('Add or extend coding-agent support in cc-sdd by executing the SOP ... end-to-end') and a concrete when ('Use when introducing a new agent, adding a subagent-capable variant, or evaluating migration ...'). This matches anchor 5's 'clearly and explicitly answers both what AND when with concrete trigger phrases'.	5 / 5
Trigger Term Quality	'introducing a new agent', 'adding a subagent-capable variant', 'evaluating migration', and 'skills-based templates' are natural phrases a user would say in this niche. A few synonymous phrasings (e.g. 'onboard an agent', 'integrate a new CLI') are missing, so it stops short of anchor 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	The description is anchored to the cc-sdd tool with specific repo paths, and its triggers (new agent, subagent-capable variant, skills-based migration) form a clear niche with minimal overlap risk against generic skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: gotalab/cc-sdd
Path: .agents/skills/cc-sdd-new-agent/SKILL.md
Commit: e2a0c67

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.