Nx Generate
nomcopter/react-mosaic
Generate code using nx generators. An agent skill from nomcopter/react-mosaic.
Log a harness lesson / post-incident so the SYSTEM improves, not just this one bug — fires on "log a harness lesson", "post-incident", "we should make this less likely", System-Evolution moments.
Install New Feedback
$ npx skills add PromptPartner/agentsmith --skill new-feedback -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install PromptPartner/agentsmith new-feedback --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/PromptPartner/agentsmith.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/new-feedback .claude/skills/new-feedback && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "new-feedback" agent skill from https://github.com/PromptPartner/agentsmith/tree/master/skills/new-feedback into .claude/skills/new-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "new-feedback", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/PromptPartner/agentsmith/tree/master/skills/new-feedbackType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add PromptPartner/agentsmith --skill new-feedback -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install PromptPartner/agentsmith new-feedback --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PromptPartner/agentsmith.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/new-feedback .agents/skills/new-feedback && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "new-feedback" agent skill from https://github.com/PromptPartner/agentsmith/tree/master/skills/new-feedback into .agents/skills/new-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "new-feedback", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add PromptPartner/agentsmith --skill new-feedback -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install PromptPartner/agentsmith new-feedback --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PromptPartner/agentsmith.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/new-feedback .cursor/skills/new-feedback && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "new-feedback" agent skill from https://github.com/PromptPartner/agentsmith/tree/master/skills/new-feedback into .cursor/skills/new-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "new-feedback", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/PromptPartner/agentsmith.git --path skills/new-feedback--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add PromptPartner/agentsmith --skill new-feedback -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install PromptPartner/agentsmith new-feedback --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PromptPartner/agentsmith.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/new-feedback .gemini/skills/new-feedback && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "new-feedback" agent skill from https://github.com/PromptPartner/agentsmith/tree/master/skills/new-feedback into .gemini/skills/new-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "new-feedback", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install PromptPartner/agentsmith new-feedbackInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add PromptPartner/agentsmith --skill new-feedback -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/PromptPartner/agentsmith.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/new-feedback .github/skills/new-feedback && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "new-feedback" agent skill from https://github.com/PromptPartner/agentsmith/tree/master/skills/new-feedback into .github/skills/new-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "new-feedback", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add PromptPartner/agentsmith --skill new-feedback -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install PromptPartner/agentsmith new-feedback --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PromptPartner/agentsmith.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/new-feedback .opencode/skills/new-feedback && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "new-feedback" agent skill from https://github.com/PromptPartner/agentsmith/tree/master/skills/new-feedback into .opencode/skills/new-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "new-feedback", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
new-feedback- GitHub stars
- 177
- Token cost
- ~608 tokens
- SKILL.md length
- 275 words
- Files
- 1
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- MIT
At a glance
Log a harness lesson / post-incident so the SYSTEM improves, not just this one bug — fires on "log a harness lesson", "post-incident", "we should make this less likely", System-Evolution moments.
- Works in 2 steps: Next number = (highest existing… → Create docs/feedback/NNNN-.md (Status:…
- Tasks that involve Project scaffolding
- SKILL.md covers When this fires, Absence gate, Fast path — if the Agentsmith… and Fallback — no CLI, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
New Feedback is an agent skill from PromptPartner/agentsmith. Log a harness lesson / post-incident so the SYSTEM improves, not just this one bug — fires on "log a harness lesson", "post-incident", "we should make this less likely", System-Evolution moments. Part of the Agentsmith harness; scaffolds a numbered docs/feedback/NNNN-.md with the five-stage template (R9 — numbers are never reused).
Its SKILL.md is about 610 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Requires filesystem access; the fast path requires the cross-platform Agentsmith CLI.
It sits in Development, covering Project scaffolding. The repository describes itself as: Universal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembled by one setup script. The licence is MIT.
When your agent uses it
- Tasks that involve Project scaffolding
Example prompts
- “log a harness lesson”
- “post-incident”
- “we should make this less likely”
- “/new-feedback”
Requirements
- Compatibility (from SKILL.md): Requires filesystem access; the fast path requires the cross-platform Agentsmith CLI.
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- Next number = (highest existing docs/feedback/NNNN-*.md + 1), zero-padded to 4 digits.
- Create docs/feedback/NNNN-.md (Status: open) with the five stages
What it can do on your machine
Read from SKILL.md and the folder at commit b293c3a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
Requires filesystem access; the fast path requires the cross-platform Agentsmith CLI.
From compatibility in the SKILL.md frontmatter.
Context cost
New Feedback loads about 608 tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 275 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from PromptPartner/agentsmith at commit b293c3a, republished under its MIT licence (© PromptPartner). 275 words, ~608 tokens.
Download SKILL.mdSave it as
.claude/skills/new-feedback/SKILL.md (or your agent's skills folder).- name
- new-feedback
- description
- Log a harness lesson / post-incident so the SYSTEM improves, not just this one bug — fires on "log a harness lesson", "post-incident", "we should make this less likely", System-Evolution moments. Part of the Agentsmith harness; scaffolds a numbered docs/feedback/NNNN-*.md with the five-stage template (R9 — numbers are never reused).
- compatibility
- Requires filesystem access; the fast path requires the cross-platform Agentsmith CLI.
New feedback note (harness post-incident)
The point is not to fix THIS bug — it's to change the SYSTEM so this whole CLASS is less likely (core/60). Small, specific, traceable to the incident.
When this fires
You were corrected on something a rule could have prevented; you iterated more than you should have; a human stepped in; you re-derived a decision a past session already made. After fixing the immediate thing, capture the lesson.
Absence gate
Before filing or implementing a missing-item defect, confirm absence with an exact, count-based, or untruncated result. Truncated, paginated, filtered, or summarized search output is incomplete evidence.
Fast path — if the Agentsmith CLI is available
Run agentsmith new-feedback "short symptom" — use .agentsmith/agentsmith on macOS/Linux or
.agentsmith\\agentsmith.cmd on Windows when the command is not on PATH. It computes the next number and writes
docs/feedback/NNNN-<slug>.md with the five-stage template, Status open.
Fallback — no CLI
- Next number = (highest existing
docs/feedback/NNNN-*.md+ 1), zero-padded to 4 digits. Numbers are never reused (R9), even if an old entry was archived. - Create
docs/feedback/NNNN-<slug>.md(Status: open) with the five stages:- Evidence / symptom — what was observed, quoted.
- Failure mechanism — WHY the system allowed it (missing rule / vague instruction / absent guardrail / unreached tool / noisy context — almost never "the model was dumb").
- Bounded edit — the smallest change that prevents the whole class.
- Named surface — exactly where it lands (a core rule, a hook, a verify phase, a template); prefer a deterministic surface over prose the model can skip.
- Non-regression — the check that stays red on recurrence. Until it's real, Status stays open.
Report
Name the file, then land the bounded edit on its named surface and flip Status to applied.
© PromptPartner, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/new-feedback of PromptPartner/agentsmith.
Open the folder on GitHubat commit b293c3a
Compare with similar skills
New Feedback next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| New Feedback this skillPromptPartner/agentsmith | 177 | — | ~608 | Automated safety check: Pass | MIT | |
| Nx Generatenomcopter/react-mosaic | 4.8k | 7 repos | ~1.9k | Automated safety check: Pass | Custom licence | |
| PonytailDavidObando/gsharp | 564 | 8 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Run Nx Generatornrwl/nx | 29k | 2 repos | ~592 | Automated safety check: Notes | MIT | |
| Conductor Setupgemini-cli-extensions/conductor | 3.8k | — | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Mirage VFS Adapter Authoringstrukto-ai/mirage | 3.7k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Ponytail
DavidObando/gsharp
Forces the laziest solution that actually works, simplest, shortest, most minimal.
Run Nx Generator
nrwl/nx
Run Nx generators with prioritization for workspace-plugin generators.
Conductor Setup
gemini-cli-extensions/conductor
Scaffolds the project and sets up the Conductor environment.
Mirage VFS Adapter Authoring
strukto-ai/mirage
Builds or extends a custom Mirage virtual filesystem adapter for an API, database, object store or app data, with a working mount configuration and filesystem tests.
Siteboon Backend Module Standards
siteboon/claudecodeui
Enforces this repository's TypeScript backend module architecture under server/: feature folders, barrel exports, and where shared types and utilities belong.
More from PromptPartner/agentsmith
All 10 skills in this repoAutonomous Run
PromptPartner/agentsmith
Prepare, start, inspect, resume, or stop a finite local overnight coding run after a human has accepted a Wayfinder terminal spec; coordinates a declared Claude/Codex maker and independent checker…
Grill With Docs
PromptPartner/agentsmith
Grill a fuzzy, single-session repository change into shared language, recorded decisions, and a handoff-ready plan.
Wayfinder
PromptPartner/agentsmith
Wayfind a foggy, multi-session effort into an accepted repository spec and separate implementation-ticket drafts.
Handoff
PromptPartner/agentsmith
Checkpoint work for recovery — fires on "handoff", "wrap up", context pressure, a closed phase, or before a long external wait or irreversible gate.
Harness Doctor
PromptPartner/agentsmith
Check whether this project's Agentsmith harness is installed correctly and healthy — fires on "is my harness set up right?", "harness doctor", "check my harness".
Harness Help
PromptPartner/agentsmith
Orient a non-coder to this project's Agentsmith harness — fires on "what is this harness?", "what are my rules?", "which profile am I on?", "what do I type next?".
Related
Categories
Questions about New Feedback
What does New Feedback do?
Log a harness lesson / post-incident so the SYSTEM improves, not just this one bug — fires on "log a harness lesson", "post-incident", "we should make this less likely", System-Evolution moments. New Feedback is an agent skill from PromptPartner/agentsmith. Log a harness lesson / post-incident so the SYSTEM improves, not just this one bug — fires on "log a harness lesson", "post-incident", "we should make this less likely", System-Evolution moments.
When should I use New Feedback?
New Feedback fits situations like: tasks that involve Project scaffolding.
How do I install New Feedback in Claude Code?
Run `npx skills add PromptPartner/agentsmith --skill new-feedback -a claude-code`. Or copy the skill folder (skills/new-feedback in PromptPartner/agentsmith) into .claude/skills/new-feedback in your project. Claude Code loads it when a task matches its description.
How do I install New Feedback in Codex?
Run `npx skills add PromptPartner/agentsmith --skill new-feedback -a codex`. Or copy the skill folder (skills/new-feedback in PromptPartner/agentsmith) into .agents/skills/new-feedback in your project. Codex loads it when a task matches its description.
Can I use New Feedback in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add PromptPartner/agentsmith --skill new-feedback -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/new-feedback, .gemini/skills/new-feedback, .github/skills/new-feedback and .opencode/skills/new-feedback in your project.
What does New Feedback need to run?
SKILL.md names no scripts, command-line tools or credentials: New Feedback is instructions for the agent only. Compatibility (from SKILL.md): Requires filesystem access; the fast path requires the cross-platform Agentsmith CLI..
Does New Feedback access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is New Feedback safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does New Feedback use?
New Feedback is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does New Feedback use?
About 608 tokens (SKILL.md is roughly 2.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to New Feedback?
Skills that share tags, products or a category with New Feedback: Nx Generate (nomcopter/react-mosaic, 4.8k stars), Ponytail (DavidObando/gsharp, 564 stars), Run Nx Generator (nrwl/nx, 29k stars) and Conductor Setup (gemini-cli-extensions/conductor, 3.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains New Feedback?
PromptPartner (a GitHub user) maintains it in PromptPartner/agentsmith, which has 177 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 7, 2026.
Source: PromptPartner/agentsmith on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.