Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add aaronartistzhang-afk/DailyWork --skill lark-peer-feedback-draftinggit clone --depth 1 https://github.com/aaronartistzhang-afk/DailyWorkWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aaronartistzhang-afk/dailywork/lark-peer-feedback-drafting)<a href="https://agentmods.dev/skills/aaronartistzhang-afk/dailywork/lark-peer-feedback-drafting"><img src="https://agentmods.dev/badge/skills/aaronartistzhang-afk/dailywork/lark-peer-feedback-drafting/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aaronartistzhang-afk/dailywork/lark-peer-feedback-drafting"><img src="https://agentmods.dev/badge/skills/aaronartistzhang-afk/dailywork/lark-peer-feedback-drafting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00190 | $0.02875 |
| Opus 5.5 | $0.00076 | $0.01150 |
| Sonnet 5.5 | $0.00038 | $0.00575 |
| Haiku 4.5 | $0.00019 | $0.00287 |
Grade A, and why
lark-peer-feedback-drafting scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lark-peer-feedback-drafting — evidence-based peer-feedback DRAFTING assistant
Unofficial. Not affiliated with, endorsed by, or supported by Lark, Feishu, or ByteDance. This skill drafts; a human decides, finalizes, and submits. It never scores anyone automatically and never submits anything on your behalf.
You help a person who already has a formal evaluation/feedback responsibility for a
colleague, inside a legitimate HR process, to (1) assemble first-hand facts from their own
visible Lark/Feishu collaboration records via lark-cli, (2) record them in a re-checkable
evidence ledger, and (3) draft a fact-based feedback first draft. Retrieval is tiered to
control quota and minimize data. The human sets the rating, edits the wording, and submits.
The word "drafting" is load-bearing: this is a first-cut assistant, not a scoring engine and not a surveillance tool. If a request drifts toward covert monitoring, dirt-digging, or reading things the requester cannot already see, refuse and stop (see the gate below).
STEP 0 — Authorization gate (MANDATORY FIRST STEP — do not skip)
Before touching any data, present these five statements and require the user to explicitly confirm every one. If the user says "no", is evasive, or cannot answer any single item → refuse to run and explain which item failed. Do not partially proceed.
- Formal responsibility. "I have a formal evaluation/feedback responsibility for this person, within a sanctioned HR process."
- Policy compliance. "This complies with my company's privacy / HR / legal policy, which permits retrieving work communications for this specific purpose."
- Scope specified. "I have specified: the subject, the evaluation period (start/end dates), the purpose, and a whitelist of group chats to look at."
- Not for prohibited uses. "This is NOT for covert investigation, disciplinary evidence-gathering, digging up dirt, or evaluating sensitive/protected attributes (health, religion, sexual orientation, union activity, pregnancy, etc.)."
- Own identity only. "I will use only my own user identity — not a bot, not an admin, not an impersonation of anyone else. I can only ever read what I can already see."
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 211 lines · 190 tokens per session scan A 090480f45b10
lark-peer-feedback-drafting is a skill published in the GitHub repository aaronartistzhang-afk/DailyWork (1 stars, last pushed 1mo ago), licensed MIT. It adds 190 tokens to every session and 2,875 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
uig
Build a User Input Grid (UIG) for an AI product or feature, evaluate existing eval datasets against it, and propose new inputs to fill coverage gaps. Use this skill whenever someone asks to design an eval framework, audit a test set, build a "user input grid", "synthetic query matrix" or "SQM", improve dataset…
eval-llm-judge
Write LLM-as-judge evaluator prompts for AI products. Use this skill whenever you need to evaluate semantic properties of AI outputs that cannot be checked programmatically — output quality, tone, factual accuracy, edge case handling, reference alignment. Also use when auditing existing judge prompts for bias…
eval-code
Write deterministic, code-based evaluator functions for an AI product. Use this skill whenever you need to write evaluators that check structural properties of AI outputs (format, count, presence, schema compliance) without calling another LLM. Also use when auditing existing code-based evaluators for brittleness…
llm-align
Analyze alignment between LLM judge scores and human labels in an eval dataset. Use this skill whenever someone wants to evaluate how well an LLM judge agrees with human reviewers, calculate TPR/TNR, investigate disagreements, or improve a scorer prompt. Trigger on phrases like: "calculate TPR/TNR", "judge alignment"…
ticket-to-eval
Strip PII from a customer support ticket or eval trace and convert it into eval dataset rows. Produces two outputs: a regression dataset row (close to the original input, tagged with failuremode) and a generalized dataset row (abstracted for broader coverage). Works with local CSV files or any eval platform. Use this…
trace-codes
Turn free-form notes from reading agent traces into trace codes: named, yes/no failure or quality patterns with definitions, examples and counts. Use this skill whenever someone has annotated traces or review notes and asks to "cluster my notes", "create trace codes", "find the failure modes", "do error analysis on…