tlc-spec-driven

Feature planning and implementation with 4 adaptive phases (Specify, Design, Tasks, Execute). Auto-sizes depth by complexity. Writes testable requirements in EARS notation, atomic tasks, atomic Conventional Commits, and requirement traceability. Ships deterministic Python validation scripts so structural gates are enforced by code, not memory. Features an independent Verifier (author != verifier, evidence-or-zero), a discrimination sensor, a decision log (STATE.md), a test-coverage matrix, and a self-improving lessons layer. Stack-agnostic and tool-agnostic. Use when (1) planning features, (2) implementing with verification and atomic commits, (3) validating an implementation against a spec. Triggers on "specify feature", "discuss feature", "design", "tasks", "implement", "validate", "verify work", "UAT", "record decision", "pause work", "resume work". Do NOT use for pure architecture decomposition analysis or standalone technical design documents.

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

77%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.

The body is a well-structured, actionable overview with strong validation checkpoints and clean progressive disclosure to 12 real reference files. Its main weakness is redundancy: the Verifier and several emphatic guardrails are restated across sections and could be consolidated.

Suggestions

Consolidate the Verifier description into a single section (Sub-Agent Delegation) and have Critical Rules #4 cross-reference it instead of re-explaining it.

Trim repeated emphatic phrases ('never optional and never prompted', 'always-on, never prompted', 'non-negotiable') to a single statement each to reduce token cost.

Where possible, replace placeholder command args (e.g. '<spec-path-or-feature>') with a one-line concrete example invocation to push actionability toward copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and it assumes Claude's competence (no basic-concept explanations), but the Verifier is described twice (Critical Rules #4 and again fully in Sub-Agent Delegation) and emphatic phrases like 'never optional and never prompted' / 'always-on, never prompted' repeat, so it could be tightened.	3 / 5
Actionability	Concrete executable commands throughout — 'python3 <skill-dir>/scripts/validate_spec.py', 'validate_tasks.py', 'check_commit.py --message', 'validate_state.py', 'lessons.py list --status confirmed' — with specific file paths and the .specs tree; held back from 5 by placeholder args like '<spec-path-or-feature>' and the <skill-dir> substitution.	4 / 5
Workflow Clarity	Phases are clearly sequenced (Specify → Design → Tasks → Execute) with explicit validation gates before each milestone, a 'non-zero exit means STOP and fix' checkpoint, and a bounded fix→re-verify feedback loop (max 3 iterations) for destructive/batch commit operations.	5 / 5
Progressive Disclosure	SKILL.md is an overview that points to one-level-deep, clearly signaled reference links (specify.md, discuss.md, design.md, tasks.md, implement.md, validate.md, memory.md, lessons.md, sub-agents.md, coding-principles.md, code-analysis.md, context-limits.md), all of which exist in references/; content is appropriately split and easy to navigate.	5 / 5
	Total	17 / 20 Passed

Description

100%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.

The description is comprehensive, concrete, and well-targeted: it states specific capabilities, enumerates natural trigger phrases, and provides explicit use/exclusion guidance. It is dense but every clause earns its place.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Writes testable requirements in EARS notation, atomic tasks, atomic Conventional Commits, and requirement traceability', 'Ships deterministic Python validation scripts', independent Verifier, discrimination sensor, decision log, lessons layer — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ('Feature planning and implementation with 4 adaptive phases...') and when ('Use when (1)... (2)... (3)... Triggers on...', plus a 'Do NOT use for...' exclusion) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases users would actually say: 'specify feature', 'discuss feature', 'design', 'tasks', 'implement', 'validate', 'verify work', 'UAT', 'record decision', 'pause work', 'resume work'.	5 / 5
Distinctiveness Conflict Risk	Clear niche (spec-driven development with deterministic gates) and an explicit exclusion ('Do NOT use for pure architecture decomposition analysis or standalone technical design documents') minimize conflict with other skills.	5 / 5
	Total	20 / 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: tech-leads-club/agent-skills
Path: packages/skills-catalog/skills/(development)/tlc-spec-driven/SKILL.md
Commit: fc886b7

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.