lintlang-release
Prepare, verify, publish, resume, or dry-run a LintLang release from merged main.
Skill by hermes-labs-ai
Chalk Labs
Need help deploying lintlang-release?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/hermes-labs-ai-lintlang-release
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/lintlang-release
What's inside
- Skill name
lintlang-release- Description
- Prepare, verify, publish, resume, or dry-run a LintLang release from merged main. Use for release readiness, version synchronization, release publication, or post-release closeout. This entrypoint selects one phase of the maintained release protocol and delegates mechanical work to the repository's existing scripts and workflow.
- License
- Apache-2.0
- Compatibility
- Requires a LintLang repository checkout; public release steps also require normal GitHub and PyPI maintainer access.
- Instructions
- 72 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Release LintLang
This skill is a navigation entrypoint, not a second release system. Release only
changes already merged to `main`; do not pull in an unmerged feature, false-positive
experiment, classifier change, or another worktree merely because it is nearby.
## Select one phase
Read the [release protocol entry document](https://docs.google.com/document/d/1jac3QfhDxnnf9iMWNdLRw0ByL7HgNaUhJ-Jflq37t2Y/edit)
with an authorized connected Google Drive tool. Then read only the phase that
matches public state:
- [01 — Prepare & verify](https://docs.google.com/document/d/1tcXacj0cF07P4EJk1ii7gxvkonqd8eAHenwU7m5ef7g/edit): no verified GitHub/PyPI release yet.
- [02 — Publish & verify](https://docs.google.com/document/d/1K6E_3E8zitQOWJN5k67oFsb0OvEk-eIEyv-UmK9qBNc/edit): the candidate is verified and publication is next or in progress.
- [03 — Synchronize & close](https://docs.google.com/document/d/1RG3bG204R83X44OfpdspAy2ebFPru_I1PA_9kMKkWA4/edit): the GitHub release and PyPI distributions are independently verified.
Do not assume that a bare Drive URL is readable. If the connected document is
unavailable, the repository-local dry run below is still safe, but stop before a
public or cross-repository mutation and report the missing phase context. Treat an
old version number in the protocol as process context, never as a release fact.
Resolve the requested version and public state from the current checkout, GitHub
tag/release, and PyPI.
## Dry-run or prepare
Work in a clean branch or worktree from current `origin/main`. Let `VERSION` be the
explicit release version; use the version in `pyproject.toml` only for a no-change
current-state dry run.
```bash
python scripts/sync-version-docs.py --version "$VERSION" --check
```
Exit `0` means the controlled current-version surfaces are already synchronized.
Exit `1` lists the files that preparation would change; it is expected for a new
version. The command does not write. To prepare those mechanical changes, remove
`--check`, review the diff, then run the check again.
Create and review `.github/releases/v${VERSION}.md` for the requested release.
Derive its claims and contributor credits from the merged release diff and merged
pull requests. Credit external contributors by handle and contribution; do not
guess authorship. Keep historical and explicitly held pins unchanged.
After preparation, verify the existing contracts rather than inventing another
publisher:
```bash
python scripts/verify_release_tag.py --tag "v$VERSION"
python -m pytest -q tests/test_version_consistency.py tests/test_publish_workflow.py tests/test_systemic_automation.py
ruff check src/ tests/
python -m build
python -m twine check --strict dist/*
```
Run the repository's full required checks and independent review required by the
active phase before crossing its gate.
## Publish or close
`.github/workflows/publish.yml` is the only package release workflow. A pushed
`v*` tag starts publication; `workflow_dispatch` is recovery for an existing tag.
Do not create another release workflow, upload a separately built distribution, or
infer PyPI success from a green GitHub job. Follow Phase 02 and verify the actual
GitHub assets plus fresh installs from both the public wheel and sdist.
After publication, follow Phase 03. Re-run `sync-version-docs.py --check` for this
repository, classify current versus historical or held references before changing
them, use each controlled site's own update/deploy mechanism, and verify rendered
public surfaces. Record exact tag, commit, artifact hashes, checks, links,
contributors, and intentional exceptions in the normal PR/release trace.From hermes-labs-ai/lintlang, Apache-2.0.
More from hermes-labs-ai/lintlang
- 0.783score
lintlang
hermes-labs-ai
Use when writing or reviewing AI agent configs, system prompts, or tool definitions (JSON/YAML/Python) and you need to catch ambiguous tool descriptions…
SkillAFreshness: A★ 143Claude Code +9 - 0.783score
lintlang-audit
hermes-labs-ai
Audit a named AI agent config, system prompt, tool-definition or instruction file (YAML, JSON, Markdown, text, or Python) with the released LintLang CLI, on…
SkillAFreshness: A★ 143Claude Code +9 - 0.783score
lintlang-audit
hermes-labs-ai
Audit a named AI agent config, system prompt, tool definition, or instruction file (YAML, JSON, Markdown, text, or Python) with the released LintLang CLI in…
SkillAFreshness: A★ 143Claude Code +9 - 0.783score
lintlang
hermes-labs-ai
Lint AI agent instruction files (SKILL.md, CLAUDE.md, AGENTS.md, GEMINI.md), tool definitions, system prompts, and agent configs with the deterministic…
SkillAFreshness: A★ 143Claude Code +9 - 0.642score
missing-trigger
hermes-labs-ai
Writes a status summary from a template.
SkillAFreshness: A★ 143Claude Code +9
Signals
- Stars
- 143
- Forks
- 13
- Open issues
- 4
- Last commit (this folder)
- Oct 20, 2026 (10 days ago)
- Last release
- Oct 20, 2026 (10 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/hermes-labs-ai/lintlang
- Website
- lintlang.ai/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from hermes-labs-ai
- 0.783score
lintlang-audit
hermes-labs-ai
Audit a named AI agent config, system prompt, tool definition, or instruction file (YAML, JSON, Markdown, text, or Python) with the released LintLang CLI in…
SkillAFreshness: A★ 143Claude Code +9 - 0.783score
lintlang
hermes-labs-ai
Lint AI agent instruction files (SKILL.md, CLAUDE.md, AGENTS.md, GEMINI.md), tool definitions, system prompts, and agent configs with the deterministic…
SkillAFreshness: A★ 143Claude Code +9 - 0.783score
lintlang
hermes-labs-ai
Use when writing or reviewing AI agent configs, system prompts, or tool definitions (JSON/YAML/Python) and you need to catch ambiguous tool descriptions…
SkillAFreshness: A★ 143Claude Code +9 - 0.783score
lintlang-audit
hermes-labs-ai
Audit a named AI agent config, system prompt, tool-definition or instruction file (YAML, JSON, Markdown, text, or Python) with the released LintLang CLI, on…
SkillAFreshness: A★ 143Claude Code +9 - 0.656score
little-canary
hermes-labs-ai
Use when you need to screen inbound untrusted text before it reaches a primary model — detecting prompt injection by its behavioral effect on a sacrificial…
SkillAFreshness: A★ 41Claude Code +9 - 0.645score
Fidelis Memory
hermes-labs-ai
Recall locally stored agent memories through an MCP-compatible host.
ConnectorAFreshness: ALocal★ 24↓ 66/wkClaude Code +5
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get lintlang-release running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
lintlang-release skill. Agent Mart. https://agentmart.dev/skills/hermes-labs-ai-lintlang-release (last updated 2026-10-24)