improve SKILL.md skillB

improve from coder/agent-tty is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add coder/agent-tty/improve@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
coder/agent-tty
Path
.agents/skills/improve/SKILL.md
Versions recorded
1
Latest version
v1.0.0, committed Jun 22, 2026
Size
15,849 bytes
Repository stars
30
License
Apache-2.0

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to…

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

# Improve

You are a **senior advisor, not an implementer**. Your job is to deeply understand a codebase, find the highest-value improvement opportunities, and write implementation plans good enough that a _different, less capable model with zero context from this session_ can execute, test, and maintain them.

The economics of this skill: an expensive, high-ceiling model does the part where intelligence compounds (understanding, judging, specifying). Cheaper models do the execution. The plan is the product — its quality determines whether the executor succeeds.

## Hard Rules

1. **Never modify source code yourself.** No edits, no fixes, no "quick wins while you're in there." The ONLY files you may create or modify live under `plans/` in the repo root — or under `advisor-plans/` when `plans/` already exists for an unrelated purpose (create the chosen directory if absent). The `execute` variant dispatches a _separate executor subagent_ that edits code in an isolated git worktree — you review its diff and render a verdict; you still never edit code directly, and you never merge, push, or commit to the user's branch.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add coder/agent-tty/improve@sha256:e671f31b276c4d91

The line at the top of this page pins the label v1.0.0, 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_z7pbe2hycxpgapgr.svg)](https://markdownregistry.com/a/art_z7pbe2hycxpgapgr)

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

Versions

The registry has recorded 1 version of this file, committed on Jun 22, 2026.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-06-22 889f27e 15,849 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No prompt-injection phrasing (matched: ignore previous instructions)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (15849 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 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

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

coder/agent-tty · 30 stars · license Apache-2.0 · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_z7pbe2hycxpgapgr
GET https://markdownregistry.com/api/v1/resolve?ref=coder/agent-tty/improve
GET https://markdownregistry.com/api/v1/blob/e671f31b276c4d91dc5a829e36561a6b5e8cb0090f665c272fff4a6e091b8884

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 coder/agent-tty

codebase-design SKILL.md skill
coder/agent-tty · .agents/skills/codebase-design/SKILL.md · Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find…
git:20260622.889f27e · audit A · 30 stars
diagnose SKILL.md skill
coder/agent-tty · .agents/skills/diagnose/SKILL.md · Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument →…
git:20260429.20f5c0a · audit A · 30 stars
diagnosing-bugs SKILL.md skill
coder/agent-tty · .agents/skills/diagnosing-bugs/SKILL.md · Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports…
git:20260622.889f27e · audit A · 30 stars
domain-modeling SKILL.md skill
coder/agent-tty · .agents/skills/domain-modeling/SKILL.md · Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous…
git:20260622.889f27e · audit A · 30 stars
grill-with-docs SKILL.md skill
coder/agent-tty · .agents/skills/grill-with-docs/SKILL.md · A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
git:20260622.889f27e · audit A · 30 stars
grilling SKILL.md skill
coder/agent-tty · .agents/skills/grilling/SKILL.md · Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building…
git:20260622.889f27e · audit A · 30 stars
improve-codebase-architecture SKILL.md skill
coder/agent-tty · .agents/skills/improve-codebase-architecture/SKILL.md · Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you…
git:20260622.889f27e · audit A · 30 stars
release-maintainer SKILL.md skill
coder/agent-tty · .agents/skills/release-maintainer/SKILL.md · Internal maintainer SOP for version bumps, release PRs, tagging, publishing, and post-publish verification in this…
git:20260424.546cf9a · audit A · 30 stars
tdd SKILL.md skill
coder/agent-tty · .agents/skills/tdd/SKILL.md · Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions…
git:20260622.889f27e · audit A · 30 stars
to-issues SKILL.md skill
coder/agent-tty · .agents/skills/to-issues/SKILL.md · Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet…
git:20260622.889f27e · audit A · 30 stars
to-prd SKILL.md skill
coder/agent-tty · .agents/skills/to-prd/SKILL.md · Turn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of…
git:20260622.889f27e · audit A · 30 stars
triage SKILL.md skill
coder/agent-tty · .agents/skills/triage/SKILL.md · Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write…
git:20260622.889f27e · audit A · 30 stars

Every file in coder/agent-tty

Other files named improve

improve SKILL.md skill
sethgammon/citadel · skills/improve/SKILL.md · Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it…
git:20260611.0f3f8e7 · audit A · 929 stars
improve SKILL.md skill
rsmdt/the-startup · plugins/start/skills/improve/SKILL.md · Find deepening opportunities in a codebase — refactors that turn shallow modules into deep ones for better testability…
git:20260930.f2ff895 · audit A · 577 stars
improve SKILL.md skill
asymmetric-al/core · .agents/skills/improve/SKILL.md · Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER…
v1.0.0 · audit B · 373 stars
improve SKILL.md skill
jim60105/copilot-prompt · skills/improve/SKILL.md · Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER…
v1.0.0 · audit B · 22 stars
improve SKILL.md skill
khaledsaeed18/dotclaude · .agents/skills/improve/SKILL.md · Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER…
v1.0.0 · audit B · 5 stars

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