skill-enhance SKILL.md skillA

skill-enhance from techygarg/lattice is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add techygarg/lattice/skill-enhance@git:20261009.a96f344

Pins git:20261009.a96f344 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
techygarg/lattice
Path
dev-skills/skill-enhance/SKILL.md
Versions recorded
2
Latest version
git:20261009.a96f344, committed Oct 9, 2026
First version recorded
Aug 25, 2026
Size
7,470 bytes
Repository stars
206
License
MIT

Full enhancement pipeline for an existing Lattice skill — rewrites a molecule or atom to modern-capable-model grade: restores degraded grammar, deduplicates, hardens gates and branching to one-unambiguous-action precision, verifies zero behavioral loss against a pre-capture diff, then runs the combined QA gate (skill-review, skill-tighten, skill-validate) and an independent fresh-context verifier, fixing everything found. Consumer-first: optimized for first-time open-source users on fresh…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Skill Enhance

**Core responsibility:** Take one existing Lattice skill from current state to modern-capable-model grade through a fixed pipeline: baseline → dependency map (background agent) → precision rewrite with guaranteed behavior preservation → combined three-skill QA → independent verification. The skill being enhanced must end up smaller-or-equal in redundancy, fully grammatical, convention-complete, and provably non-regressive. Organizing objective: **deterministic execution** — every sentence has exactly one reading, every reachable state exactly one action, every cross-file reference literally true. Acceptance test: two different capable models reading any sentence would act identically on it.

**Input:** One skill path or name (any tier). Molecules are the primary case.

**Output:** Edited files + close-out report.

**STOP: NEVER commit, push, stash, checkout, reset, or run `build-codex-plugin.sh`. Working tree only — surface install/mirror commands for the user instead.**

**How to verify this skill did its job:**
- Pre-capture git diff exists; every preserved behavior in it is confirmed present after rewrite
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add techygarg/lattice/skill-enhance@sha256:4fb8e578452e62e4

The line at the top of this page pins the label git:20261009.a96f344, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_r4ryidopfia3qudp.svg)](https://markdownregistry.com/a/art_r4ryidopfia3qudp)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Aug 25, 2026 and Oct 9, 2026, about one every 45 days.

versioncommittedcommitsizeaudit
git:20261009.a96f344 latest2026-10-09 a96f344 7,470 BA view · diff
git:20260825.5ffcc4f2026-08-25 5ffcc4f 7,183 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7470 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

techygarg/lattice · 206 stars · license MIT · pushed 2026-10-10 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_r4ryidopfia3qudp
GET https://markdownregistry.com/api/v1/resolve?ref=techygarg/lattice/skill-enhance
GET https://markdownregistry.com/api/v1/blob/4fb8e578452e62e44ab24cda68b8b1e54bcc83220f872fa18869671a94335af8

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from techygarg/lattice

AGENTS.md AGENTS.md file
techygarg/lattice · AGENTS.md
git:20260525.248b42b · audit A · 206 stars
CLAUDE.md CLAUDE.md file
techygarg/lattice · CLAUDE.md
git:20260827.76577b8 · audit A · 206 stars
skill-align SKILL.md skill
techygarg/lattice · dev-skills/skill-align/SKILL.md · Audit and fix all Lattice documentation, README, docs/, PROJECT.md, GitHub issue templates, and CLAUDE.md to ensure…
git:20260903.74fcec8 · audit A · 206 stars
skill-forge SKILL.md skill
techygarg/lattice · dev-skills/skill-forge/SKILL.md · Create a new Lattice skill — atom, molecule, or refiner — following all framework conventions. Writing skill files…
git:20261009.a96f344 · audit A · 206 stars
skill-review SKILL.md skill
techygarg/lattice · dev-skills/skill-review/SKILL.md · Deep behavioral audit of a Lattice skill — proposes 3 review personas relevant to the skill, runs independent scenario…
git:20261009.a96f344 · audit A · 206 stars
skill-tighten SKILL.md skill
techygarg/lattice · dev-skills/skill-tighten/SKILL.md · Audit any Lattice SKILL.md for language compliance — removes rationale prose, converts soft language to imperatives…
git:20261009.a96f344 · audit A · 206 stars
skill-validate SKILL.md skill
techygarg/lattice · dev-skills/skill-validate/SKILL.md · Validate any Lattice SKILL.md against all tier conventions — atoms, molecules, and refiners. Catches structural errors…
git:20261009.a96f344 · audit A · 206 stars
architecture-compass SKILL.md skill
techygarg/lattice · skills/architecture-compass/SKILL.md · Architectural thinking partner for an existing repository — scans the codebase, conducts a structured interview, agrees…
git:20261009.a96f344 · audit A · 206 stars
architecture-refiner SKILL.md skill
techygarg/lattice · skills/architecture-refiner/SKILL.md · Facilitate a structured conversation to define architecture principles for a repository. Supports multiple architecture…
git:20260903.6d09876 · audit A · 206 stars
architecture SKILL.md skill
techygarg/lattice · skills/architecture/SKILL.md · Enforce architectural rules when generating or modifying code, and validate proposed designs before approval (design…
git:20260903.6d09876 · audit A · 206 stars
bug-fix SKILL.md skill
techygarg/lattice · skills/bug-fix/SKILL.md · Investigate, reproduce, and safely fix a bug with regression protection. Composes context, diagnosis, architecture…
git:20261009.a96f344 · audit A · 206 stars
clean-code-refiner SKILL.md skill
techygarg/lattice · skills/clean-code-refiner/SKILL.md · Facilitate a structured conversation to define clean code principles for a repository. Produces a formal clean-code.md…
git:20260903.6d09876 · audit A · 206 stars

Every file in techygarg/lattice

Browse by kind, by grade A, or by owner.