self-dev-loop
Meta-loop for Remedy developing herself — self-inject, change-safety, unit tests, security gauntlet, product soak, stress, then ship gates.
Skill by AhmiDarrow
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/ahmidarrow-self-dev-loop
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: security
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 and code. 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/self-dev-loop
What's inside
- Skill name
self-dev-loop- Description
- Meta-loop for Remedy developing herself — self-inject, change-safety, unit tests, security gauntlet, product soak, stress, then ship gates. Use when self-dev, hot-inject, improve the codebase, work on RemedyAI monorepo end-to-end, or "run the full quality loop on ourselves".
- License
- Apache-2.0
- Instructions
- 126 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Self-dev loop (Remedy on Remedy) ## Goal One **ordered** playbook when the user wants Remedy to improve **this** monorepo while staying a trustworthy partner. Prefer **activating sub-skills** rather than re-inventing commands. ## When to use - Working **in** the RemedyAI repo as the project - User says self-dev, dogfood loop, full quality loop, “run gauntlet then soak” - Multi-hour sessions that must not skip security or ship discipline ## Default sequence Execute **in order**. Skip a stage only if the user explicitly narrows scope (e.g. “unit tests only”) or the stage does not apply (docs-only change). ```text 0. Orient → project-overview / AGENTS.md / git status 1. Hot-inject → self-inject (draft → test-gate → apply/rollback → restart) 2. Blast radius → change-safety 3. Implement → write-tests, refactor-safe as needed 4. Unit gates → pytest + desktop npm test/build + check_docs 5. Gauntlet → gauntlet-security (if security surface touched or user asked) 6. Soak → soak-product (if desktop/API/CUA/stream touched or user asked) 7. Stress → stress-suite (optional; after soak green or user asked) 8. Ship → project-etiquette (test → docs → build → commit → CI → publish) ``` ### Activate helpers **Never** `skill_activate` every pack (“reload all skills”). That floods context and causes endless tool loops. Rescan disk with: ``` skill_reload() ``` Then load **one** procedure at a time (or let auto-suggest inject for the task): ``` skill_activate(skill="self-dev-loop") # this meta playbook skill_activate(skill="self-inject") skill_activate(skill="gauntlet-security") skill_activate(skill="soak-product") skill_activate(skill="stress-suite") skill_activate(skill="change-safety") skill_activate(skill="project-etiquette") ``` ## Stage details (short) ### 0. Orient ```powershell git status -sb git log -5 --oneline ``` Read root `AGENTS.md` for ship gates, installer naming, smoke matrix. ### 1. Hot-inject - **Draft** a change with normal edit tools (Python sidecar or desktop SPA). - **Gate** is tests-only (pytest + npm test). Green → apply + restart sidecar / rebuild SPA; red → roll back and record in the ledger (`~/.remedy/self_inject_ledger.jsonl`). - Full mechanics: `docs/SELF_INJECT.md`. Never commit red; never leave a broken tree. ### 2–3. Change + implement - Name blast radius (chat, gateway, rails, settings, packaging). - Prefer durable fixes; keep tree runnable. - Pair with **write-tests** for behavior changes. ### 4. Unit gates (minimum always before ship) ```powershell uv run pytest -q cd desktop; npm test; npm run build uv run python scripts/check_docs.py ``` ### 5–7. Live quality (when scope needs it) | Stage | Skill | Trigger | |-------|--------|---------| | Gauntlet | **gauntlet-security** | auth, jail, SSRF, host, sanitize | | Soak | **soak-product** | CUA, browser, stream, multi-tab, “soak” | | Stress | **stress-suite** | concurrency, multi-provider, “stress/break” | Set `REMEDY_API` / `REMEDY_HOME` to the profile under test. ### 8. Ship Follow **project-etiquette** exactly: no publish on red CI; version only for real releases; desktop tag `vX.Y.Z` for installers. ## Reporting template | Stage | Result | Evidence | |-------|--------|----------| | Hot-inject | applied / rolled back / n/a | ledger + diff-id | | Blast radius | surfaces listed | | | Unit | pass/fail | commands | | Gauntlet | pass/fail/skip | | | Soak | pass/fail/skip | `docs/_full_product_soak_results.json` | | Stress | pass/fail/skip | | | Ship | commit / CI / publish | | ## Anti-patterns - Stress before unit green - Gauntlet against the wrong API port/home - Shipping without **project-etiquette** when user asked for release - Dual messenger pollers "for testing" - Committing a **red** self-inject round (never — roll back instead) - Claiming self-dev done when only the chat replied and no commands ran
From AhmiDarrow/RemedyAI, Apache-2.0.
More from AhmiDarrow/RemedyAI
- 0.624score
bioinformatics
AhmiDarrow
Use for sequence and omics work: FASTQ/BAM/VCF/GTF/BED handling and their coordinate conventions, reference builds and liftover, read QC and trimming…
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
clinical-research
AhmiDarrow
Human-subject studies run to the standard the field expects: choosing a design that can answer the question, randomisation and blinding, endpoints fixed…
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
chemistry-research
AhmiDarrow
Use when the work involves molecular structures, reactions, spectra, computational chemistry, crystallography or chemical databases.
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
comfyui
AhmiDarrow
Local ComfyUI image generation end-to-end: from a blank machine (download, install, start, fetch models, workflows) through queue/poll/download and chat embeds.
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
bevy
AhmiDarrow
Build Rust games with Bevy: ECS mental model, plugins, schedules, states, assets, 2D sprites, fast iteration (cargo check, dynamic_linking, opt-level)…
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
computational-science
AhmiDarrow
Simulation and numerics you can defend: floating-point and conditioning understood before blaming the physics, solvers chosen for the problem, convergence and…
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
stress-suite
AhmiDarrow
Live stress and break suites for Remedy API/desktop — multi-turn storms, concurrent sessions, multi-provider rotation, adversarial break battery.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
change-safety
AhmiDarrow
Blast-radius protocol before code changes — name the surface, list coupled neighbors, run paired checks, and smoke UI/chrome/messengers that unit tests miss.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
project-etiquette
AhmiDarrow
Default ship discipline for any serious project — blast radius first, then fix, test, update code/docs, build, commit, wait for CI, publish only if green.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
self-inject
AhmiDarrow
Run one test-gated self-improvement round on the Remedy codebase: draft a change, snapshot the diff, gate it with tests only, apply (restart sidecar / rebuild…
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
soak-product
AhmiDarrow
Full product soak for Remedy — API health, computer-use, plan mode, browser rail, concurrency, docs check, and sign-off artifacts.
SkillAFreshness: A★ 5Claude Code +9 - 0.616score
webui-parity
AhmiDarrow
When changing Grove, Studio, Settings, or chat chrome, keep WebUI (browser on :7400) at parity with Tauri.
SkillAFreshness: A★ 5Claude Code +9
Signals
- Stars
- 5
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Aug 4, 2026 (2 months ago)
- Last release
- Oct 19, 2026 (10 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/AhmiDarrow/RemedyAI
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from AhmiDarrow
- 0.624score
bioinformatics
AhmiDarrow
Use for sequence and omics work: FASTQ/BAM/VCF/GTF/BED handling and their coordinate conventions, reference builds and liftover, read QC and trimming…
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
chemistry-research
AhmiDarrow
Use when the work involves molecular structures, reactions, spectra, computational chemistry, crystallography or chemical databases.
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
computational-science
AhmiDarrow
Simulation and numerics you can defend: floating-point and conditioning understood before blaming the physics, solvers chosen for the problem, convergence and…
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
bevy
AhmiDarrow
Build Rust games with Bevy: ECS mental model, plugins, schedules, states, assets, 2D sprites, fast iteration (cargo check, dynamic_linking, opt-level)…
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
comfyui
AhmiDarrow
Local ComfyUI image generation end-to-end: from a blank machine (download, install, start, fetch models, workflows) through queue/poll/download and chat embeds.
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
clinical-research
AhmiDarrow
Human-subject studies run to the standard the field expects: choosing a design that can answer the question, randomisation and blinding, endpoints fixed…
SkillAFreshness: A★ 5Claude Code +9
Cite this page
self-dev-loop skill. Agent Mart. https://agentmart.dev/skills/ahmidarrow-self-dev-loop (last updated 2026-10-24)