Home / badmuriss / my-llm-kit · skills/impl/SKILL.md · GitHub

impl skillA

impl is agent-read markdown (skill) from badmuriss/my-llm-kit: Implement a requested change or approved plan, verify its outcomes, and report concrete blockers. Use graph execution only for independent work that needs durable coordination..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Impl

Complete the authorized change using the least process that can establish its
acceptance. A task does not require a separate spec or executable intake merely
because this skill was invoked.

## Select the working mode

Read the applicable repository instructions and code relevant to the request.
Use an existing decision when supplied. Otherwise choose from task evidence:

- `direct`: one bounded edit and its relevant check. No planning file or graph.
- `verified_single`: one writer with a hypothesis/check loop for uncertain behavior.
- `light_spec`: use an existing decision record, or write `decisions/<slug>.md`
  when a material architectural decision needs to survive the session.
- `graph`: use only for independently useful packets that need durable ownership,
  integration and recovery. Read [graph-execution.md](references/graph-execution.md).

Executable intake is optional outside graph. When needed, resolve the installed
`agent-graph` skill directory, then invoke its `scripts/agent_graph.py` with
`--repo <absolute-project-path>`. Use `python3` on Unix or `py -3` on Windows.
Never assume the consumer project contains the harness source.

## Keep acceptance visible
…

Read the whole file at its exact version.

How to install

Latest version
mdr add badmuriss/my-llm-kit/impl@git:20260921.471bbed
Exact content
mdr add badmuriss/my-llm-kit/impl@sha256:17f108c1ae1ed891

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_qrte72d2fjdiymlh.svg)](https://markdownregistry.com/a/art_qrte72d2fjdiymlh)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260921.471bbed latest2026-09-21 471bbed 4,369 BA view · diff
git:20260906.3d137c02026-09-06 3d137c0 3,788 BA view · diff
git:20260904.c276d1a2026-09-04 c276d1a 9,765 BA view · diff
git:20260827.09528f52026-08-27 09528f5 9,532 BA view · diff
git:20260826.7eae05d2026-08-26 7eae05d 8,356 BA view · diff
git:20260826.22b176c2026-08-26 22b176c 8,003 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, 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 (4369 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

badmuriss/my-llm-kit · 3 stars · license MIT · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_qrte72d2fjdiymlh
GET https://markdownregistry.com/api/v1/resolve?ref=badmuriss/my-llm-kit/impl
GET https://markdownregistry.com/api/v1/blob/17f108c1ae1ed891356e9bb16f05b30786d4cd70dfbe9c99529752f05b98242a

Your agent 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.

More from badmuriss/my-llm-kit

AGENTS.md agents
badmuriss/my-llm-kit · AGENTS.md
git:20260906.3d137c0 · audit A · 3 stars
AGENTS.md@instructions agents
badmuriss/my-llm-kit · instructions/AGENTS.md
git:20260923.97e81e6 · audit A · 3 stars
agent-graph skill
badmuriss/my-llm-kit · skills/agent-graph/SKILL.md · Run durable task graphs when independent work needs ownership, integration checks and recovery. Use for graph…
git:20260921.471bbed · audit A · 3 stars
computer-use skill
badmuriss/my-llm-kit · skills/computer-use/SKILL.md · Inspect and operate local browser or desktop interfaces. Prefer Jev Ultrafast for supported browser-only goals when its…
git:20260921.471bbed · audit A · 3 stars
frontend-visual-validation skill
badmuriss/my-llm-kit · skills/frontend-visual-validation/SKILL.md · Verify rendered UI changes with reproducible screenshots and vision review on their supported platforms.
git:20260906.3d137c0 · audit A · 3 stars
grill-me skill
badmuriss/my-llm-kit · skills/grill-me/SKILL.md · Adversarial interview about a plan until you reach shared understanding. use_when: "grill me", stress-test a plan or…
git:20260808.343cbe3 · audit A · 3 stars
grill-with-docs skill
badmuriss/my-llm-kit · skills/grill-with-docs/SKILL.md · Grill a plan against the documented domain model, updating CONTEXT.md and ADRs inline. use_when: stress-test a plan…
git:20260808.343cbe3 · audit A · 3 stars
ingest skill
badmuriss/my-llm-kit · skills/ingest/SKILL.md · Extract content from documents when their format or layout prevents reliable direct reading. Verify reading order and…
git:20260906.3d137c0 · audit A · 3 stars
readme-pass skill
badmuriss/my-llm-kit · skills/readme-pass/SKILL.md · Make a public repository README easier to understand and use. Apply when README structure or presentation is requested.
git:20260906.3d137c0 · audit A · 3 stars
remove-ai-marks skill
badmuriss/my-llm-kit · skills/remove-ai-marks/SKILL.md · Inspect and remove requested metadata or invisible marks from user-owned files. Use when provenance cleanup is…
git:20260906.3d137c0 · audit B · 3 stars
research skill
badmuriss/my-llm-kit · skills/research/SKILL.md · Research external questions and compare evidence with source attribution. Use for research or fact-checking, not facts…
git:20260923.97e81e6 · audit A · 3 stars
rule-curator skill
badmuriss/my-llm-kit · skills/rule-curator/SKILL.md · Audit an existing corpus of agent instructions for conflicts, duplication and unnecessary process. Use for a…
git:20260906.3d137c0 · audit A · 3 stars

Every file in badmuriss/my-llm-kit

Other files named impl

impl skill
tercel/code-forge · skills/impl/SKILL.md · Execute pending tasks for a feature — TDD-driven implementation with sub-agent isolation and progress tracking. Use…
git:20260610.fdf95d5 · audit A · 6 stars

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