tlc-spec-lean — Claude Code skill: features and installation
The tlc-spec-lean skill guides feature work from a reviewed plan through evidence-backed checks, implementation, and independent verification. Use it when requirements need to be agreed before coding begins.
CC-BY-4.0 ★ 7,191 updated 2026-11-02
npx skills add tech-leads-club/agent-skills --skill tlc-spec-lean -a claude-codeWhat tlc-spec-lean does
The agent first drafts a single plan covering EARS criteria, the user path, entities, interface, and decisions that are hard to reverse. A human reviews it before the criteria become checks with proofs. Then implementation starts; the skill does not create a task breakdown, leaving other choices to the build.
Checks use the project’s own tests or commands. When a criterion refers to a screen capture, a separate screens sub-agent reviews the saved image; a fresh Verifier examines the tests and looks for cases the criteria missed. Completion depends on validate_verification.py passing. git push, deployment, and production-data changes still need explicit approval.
What it helps with
- agree on feature criteria before implementation
- link each requirement to a check and proof
- test whether a check catches a false claim
- compare a screen against its capture
- find uncovered cases before completion
Example prompts for the agent
- Plan this feature with
tlc-spec-leanand show me the plan for review. - Turn the approved plan into proof-backed checks, then build the feature.
- Verify the finished feature independently and address the findings.
How to install tlc-spec-lean
1Skills CLI (Vercel)
npx skills add tech-leads-club/agent-skills --skill tlc-spec-lean -a claude-code2Manually: put the files in place
~/.claude/skills/tlc-spec-lean/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/tlc-spec-lean/
1Skills CLI (Vercel)
npx skills add tech-leads-club/agent-skills --skill tlc-spec-lean -a codex2Manually: put the files in place
.agents/skills/tlc-spec-lean/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add tech-leads-club/agent-skills --skill tlc-spec-lean -a cursor2Manually: put the files in place
.cursor/skills/tlc-spec-lean/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install tech-leads-club/agent-skills 'packages/skills-catalog/skills/(development)/tlc-spec-lean'2Manually: put the files in place
.github/skills/tlc-spec-lean/SKILL.md1Skills CLI (Vercel)
npx skills add tech-leads-club/agent-skills --skill tlc-spec-lean -a gemini-cli2Platform CLI
gemini skills install https://github.com/tech-leads-club/agent-skills --path 'packages/skills-catalog/skills/(development)/tlc-spec-lean'Manually: put the files in place
.devin/skills/tlc-spec-lean/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about tlc-spec-lean
How do I install tlc-spec-lean in Claude Code?
Run npx skills add tech-leads-club/agent-skills --skill tlc-spec-lean -a claude-code. The skill file is at ~/.claude/skills/tlc-spec-lean/SKILL.md.
What does tlc-spec-lean do?
It guides feature work through a human-reviewed plan, checks tied to proofs, implementation, and review by an independent Verifier.
Can I use tlc-spec-lean with an existing task list?
No. It is intended for feature work that does not already have a task list or checklist to execute.
Source text
SKILL.md · CC-BY-4.0
---
name: tlc-spec-lean
description: 'Spec-driven feature work that freezes obligations instead of the plan: one human-reviewed plan with EARS criteria, path, entities, interface and one-way doors, then proof-backed checks, then build, then an independent Verifier. Use when the user says "tlc-spec-lean", "plan feature", "specify feature", "write the checks", "build this plan", or "verify work". Do NOT use for standalone design documents unattached to a feature, architecture decomposition analysis, or work that already has a task list or checklist to execute.'
license: CC-BY-4.0
metadata:
author: Tech Leads Club - github.com/tech-leads-club
version: '2.2.0'
---
# Tech Lead's Club - Spec, Lean
Freeze the obligations. Free the plan. Prove it with someone who did not build it. Derived from tlc-spec-driven 3.3.0 (Felipe Rodrigues), tlc-plan, and tlc-implement.
```
┌──────┐ ┌────────┐ ┌───────┐ ┌────────┐
│ PLAN │ → │ CHECKS │ → │ BUILD │ → │ VERIFY │
└──────┘ └────────┘ └───────┘ └────────┘
read it obligations yours always
```
The common failure of a coding agent is a requirement that never became an active obligation,
followed by a completion claim. What works against it is a small, frozen, external obligation set
and a verifier that is not the author, so the budget goes there and not into choreographing the
model. A human confirms what must be true and how it is being built in one document; only then does
it become obligations with proofs. There is no task breakdown and no component catalogue: what is
hard to reverse gets a one-way door with its literal shape, and the rest is decided while building.
## Rules
These hold even if no reference file is read. Each one lives here; the references point back.
1. Every check is one observable claim with a concrete value plus the proof that settles it: a test
or command whose exit code decides, or, for a state a capture draws, a picture of it judged
against the capture (rule 9).
2. Tests assert what the checks say, not what the code happens to do. Do not write a test by
reading the implementation.
3. A test changes only with the claim it proves, and leaves with the code it proves, in the same
commit. Changing a test to make a suite pass hides the failure it exists to show: a wrong check
is a stop-and-ask.
4. Checks are fixed once `validate_checks.py` passes; a check may be appended when the walk or the
Verifier finds a missing obligation. In the plan, `Landing`, `Surface` and the stored shape are
additive; the path and `Changes underneath` are kept true in the commit that changes them.
5. The Verifier is a fresh sub-agent, never the author, and it always runs, once per feature,
beside the screens sub-agent. `check_proofs.py` settles the mechanical part - every proof run
and passing at `HEAD`, the build, the pictures, the walk - and the Verifier spends its time on
judgement: it opens the test each check's proof selects and says whether that test would fail
if the claim were false, then tries examples nobody named and assertions looser than their
criterion. The work is done when every finding is closed by a commit and `proofs.md` is green
at `HEAD`.
6. A proof is the project's own test command; the skill knows no test runner. Tests that run
together go on one `Run <name>: <command>` line, run once, and each check that reads it writes
`Proof: run <name> | <the line the run prints when its test passes>`, pass marker included, so
a filter that selects nothing reads `no test ran` instead of a green exit code. A command run
alone is judged by its exit code. The checks are the floor; an edge case or guard no check
names is still the work.
7. The completion gate is a script: `validate_verification.py` exits 0. The final report opens
with its last line; a red gate is said first, never left for the reader to find.
8. An approved spec authorizes local edits and local commits. `git push`, deploy and production
data changes need an explicit go-ahead for that action.
9. **A state a capture draws is one picture.** The author reaches that state and saves
`<capture>.running.png` beside the capture from a browser window at the capture's size - its
pixel size over its scale: a wider window lays the page out differently, and resizing the image
afterwards hides it. Nobody reopens the app to judge it: a screens sub-agent judges the file
([verify-screens.md](references/verify-screens.md)), and a picture whose text reads smaller than
the capture's was resized and is retaken. It matches the capture except for what
`## Differences from the source` lists. A state no capture draws, and an existing screen the
feature does not change, are proven by a test or a `walk` proof, with no picture and no judge.
10. A capture, frame or live site that comes with the request binds unless the user called it
inspiration. A binding source is changed only by the user. Removing, renaming or departing
from something it draws is asked, recorded as a decision in `.specs/STATE.md`, and listed in
the plan's `## Differences from the source` with `Confirmed: y - AD-NNN`.
11. **The files hold the run; the chat does not survive a compaction.** The user's approval is
written in plan.md as `**Approved**: <date> - user: "<their words>"` - never one the user did
not give. Each answer goes into its file in the turn it arrives. Each sub-agent goes on the
`**Dispatched:**` line of `checks.md` `## Handoff` before it is sent. After a compaction or in a
new session, re-read this file and the current phase's reference, then resume from the files
([memory.md](references/memory.md)).
## Who checks what
| Part | Runs | Cannot catch |
| --- | --- | --- |
| `check_proofs.py` (always) | every `Run` group and lone proof once at `HEAD`, one at a time, each check's line found in its run's output, the build, pictures and walk checked | a test that passes for the wrong reason |
| The Verifier (always) | each check's test read against its criterion, two examples nobody named, assertions looser than their criterion, checks that contradict a binding capture ([verify.md](references/verify.md)) | a wrong rule whose test reads as right |
| The screens sub-agent (a criterion cites a capture) | an inventory of each capture against the author's picture, every row `same` or `differs`, at a named `HEAD` ([verify-screens.md](references/verify-screens.md)) | spacing, colour and type weight; detail smaller than a screenshot shows; screens no capture draws |
## Artifacts
```
.specs/
├── STATE.md # Decisions log (AD-NNN)
├── LESSONS.md # rendered by scripts/lessons.py - do not hand-edit
├── lessons.json # machine-owned
└── features/<feature>/
├── plan.md # problem, shape, surface, doors, criteria
├── checks.md # claims + proofs, the coverage join, swept, handoff
├── captures/ # binding source files, and the author's <capture>.running.png
├── screens.md # the screens sub-agent's inventory and verdict, per picture
├── proofs.md # written by check_proofs.py: every proof at HEAD, and each run's output
└── verification.md # the Verifier's judgement of each check, and its findings closed by commits
```
For a change under roughly three files with no one-way door, write only `checks.md` with an
`## Intent` paragraph and skip `plan.md`.
## Phases
| Phase | What it produces | Reference |
| --- | --- | --- |
| Plan | problem, shape, surface, doors, criteria; the one default stop for a human | [plan.md](references/plan.md) |
| Checks | claims with proofs, every set joined member by member, the nine dimensions swept | [checks.md](references/checks.md) |
| Build | tests from the checks, the code, commits, the screens walked and saved | [build.md](references/build.md) |
| Verify | rule 5 | [verify.md](references/verify.md), [verify-screens.md](references/verify-screens.md) |
Decisions and lessons: [memory.md](references/memory.md).
## Scripts
Resolve `<skill-dir>` as the directory containing this `SKILL.md` and run
`python3 <skill-dir>/scripts/<name>.py`. Pass `--root` when cwd is not the project root. A non-zero
exit means stop and fix. Run a script rather than read it: its messages say what to change. On
Windows, where `python3` may be the Microsoft Store alias, run `python` or `py -3`.
| When | Command |
| --- | --- |
| Before presenting the plan | `validate_plan.py <feature>` |
| Before starting to build | `validate_checks.py <feature> --execute` - it also requires the plan's `**Approved**:` line, and runs the `Build:` line once: red before any change stops |
| Before each commit | `check_commit.py --message "<msg>"` - it also prints what follows the last commit |
| Before dispatching the Verifier, and after the fix | `check_proofs.py <feature>` |
| Before declaring done | `validate_verification.py <feature>` |
| At distillation | `lessons.py add ...` |
| After editing a validator or template | `selftest.py` |
`selftest.py` mutates the fixtures in `scripts/fixtures/` once per gate rule and requires every
mutant to be killed; the fixtures are also a worked example of a passing artifact set.
## Requires
| Needs | For | Without it |
| --- | --- | --- |
| Python 3.8+ (standard library only) | every script | the gates do not run; the phases still apply |
| git | `check_proofs.py` (HEAD, clean tree) | no HEAD check: say so in the report |
| Git for Windows (on Windows) | `check_proofs.py` runs proofs in its bash, because proofs are POSIX shell | proofs run in `cmd.exe` and the script warns |
| sub-agents | the Verifier and the screens sub-agent | run their file in a new session and write `self-verified`; the gate warns |
| a model that reads images | the screens sub-agent | hand the pictures and the captures to the user |
| a browser the agent can drive | saving `<capture>.running.png` and the walk | hand the steps to the user |
Test runners: none is built in. `check_proofs.py` runs the commands `checks.md` names as the
project runs them, one at a time, with no timeout; a run's own parallelism is whatever the project
configured ([checks.md](references/checks.md)).
## Output
Produce the artifact; do not narrate the phase. Lead with the verdict and state decisions plainly.
Section headings stay in English; prose follows the project; identifiers are never translated.
© Tech Leads Club - github.com/tech-leads-club · CC-BY-4.0 · tech-leads-club/agent-skills