agentsclimarketplace

Grill with docs

Skill JasonxzWen/harness-hub/skills/grill-with-docs

Load when a repository mutation creates or materially changes durable project contracts, OKF knowledge, specs, ADRs, or architecture/API/design documents; run a source-backed alignment pass that reuses grill-me's dependency-frontier batch protocol.From its SKILL.md

Install
npx -y skills add JasonxzWen/harness-hub --skill grill-with-docs

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.7 KB, 410 tokens by cl100k_base, as published. Nobody here has run it

Grill With Docs

Use this as an atomic requirements skill called directly by the native Host main Agent. It adds durable-document evidence and consistency checks to grill-me; it is not a second interview or a documentation workflow.

Scope

Use it when the mutation's input or expected output includes durable project contracts, knowledge/, specifications, ADRs, or architecture/API/design documents; temporary .harness-hub/state/ maintenance alone does not trigger this skill.

Load and apply grill-me. Build one shared unresolved-decision graph and ask the current dependency frontier in one batch. Preserve its zero-question path, recommendations, pause/defer behavior, authorization boundaries, and stopping rule.

Evidence Pass

Before asking:

  1. Read the active task state, relevant implementation and tests, and knowledge/index.md when present.
  2. Follow only relevant OKF links and their repository source anchors.
  3. Separate accepted facts, user decisions, inferences, contradictions, vocabulary conflicts, and open questions.
  4. Test important terms with concrete boundary scenarios and compare the proposed documentation with actual code behavior.
  5. Add only consequential document conflicts or durable decisions to the shared graph.

Continue autonomously on local reversible details already covered by the project contract. Do not invent a question solely to prove that an interview occurred.

Write Boundary

Do not edit knowledge or specifications during the interview. After alignment, let the main Agent update durable documents once, deduplicate facts, synchronize links/index/log where required, and run the project's deterministic validators.

Create an ADR or new knowledge page only when an existing canonical owner cannot carry the durable decision. Create no empty taxonomy or chat-derived project truth.

Return constraints, accepted details, contradictions, open questions, and source anchors to the main Agent. If nothing durable changed, say so and keep documents byte-for-byte unchanged; the project contract owns the write and deterministic OKF validation.

Read references/domain-modeling.md when the request changes vocabulary, concept relationships, or knowledge structure.

What ships with it: 2 files

1.7 KB alongside SKILL.md

references/

Gives 0 of the 12 instructions most docs writing skills give in 410 tokens

Counted across 1,637 of the 3,044 authors here whose files we hold, read 2026-08-07

  • Announce the skill at startin 54 of 1637, across 26 files
  • Convert legacy doc files before editingin 45 of 1637, across 7 files
  • Predict questions readers might askin 42 of 1637, across 4 files
  • Generate clarifying questions for initial contextin 42 of 1637, across 3 files
  • Create document scaffold with placeholder textin 42 of 1637, across 3 files
  • Brainstorm content options for each sectionin 42 of 1637, across 3 files
  • Test the document with a fresh context-less instancein 42 of 1637, across 3 files
  • Include exact file paths in every taskin 42 of 1637, across 15 files
  • Ask interview questions one at a timein 42 of 1637, across 27 files
  • Apply surgical edits during refinementin 41 of 1637, across 2 files
  • Offer structured workflow or freeformin 40 of 1637, across 1 file
  • Ask for document meta-contextin 40 of 1637, across 2 files

Said here and by no other author read

  • load and apply grill-me
  • ask the dependency frontier in one batch
  • read active task state and relevant code
  • follow only relevant OKF links and source anchors
  • separate accepted facts from contradictions and open questions
  • test important terms with concrete boundary scenarios

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,871. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.