SuperAPI AI Directory
Partner中文AI newsFavorites
Skillsharness-operations

harness-operations

Agents & models

View repository

Updated 10-16 02:39

About this skill

Harness operations

Scope

This skill owns capability selection and native mechanics, not repository policy. It never supplies publication, merge, credential, spending or cross-repo authority. AGENTS.md and the task remain the contract; native adapter prose translates tools.

Prerequisites

Determine the actual harness from session/runtime diagnostics, not a branch prefix or presence of a file. Inspect the available tool catalog and observed configured authentication. A checked-in skill does not provision a connector, CLI or token.

Procedure

  1. Identify the needed operation and whether it is read-only or an authorized mutation. Prefer an already available configured capability; do not add personal setup as a default prerequisite. Carry forward authorization for the same action and scope. Resolve routine implementation choices independently; request a human decision only when its answer is required to proceed or materially changes the intended outcome.
  2. Load only the matching native reference: Claude Code, Codex or ChatGPT Work. If the harness is different or uncertain, use observed tools and report the missing mapping instead of pretending one profile applies.
  3. For GitHub, resolve the exact repository/ref and use connected GitHub tools when available. An authenticated supported CLI is an alternative when exposed. Match operations and parameter schemas from the actual catalog; a tool name in an example is not evidence it exists in this session.
  4. Check capabilities separately: issue/PR reads, file/tree publication, run/check metadata, log bodies, commit statuses and subscriptions may have different availability. Avoid a blanket claim that a connector cannot read logs. Retain the actual error and use an equivalent exposed capability where available.
  5. For a pending human decision, use the exposed, permitted structured question tool from the matching native reference. Include the concrete choice, context and tradeoffs; wait for an explicit answer before dependent work and reconcile the decision record. Continue independent authorized work. A plain-text question or checklist is not a substitute for an available question tool. Do not re-ask settled decisions or treat silence/default selections as approval. If the question capability is unavailable, state the limitation and use the established human handoff channel; native permission and product approval gates still apply.
  6. Preserve configured identity, proxy and trust. Never print credentials, inspect secret files for values, dump the environment, or replace credentials because a token is not visible. Diagnose 401/403 using current runtime observations. Try an equivalent configured tool before requesting installation, login or broader permissions. Report the failing operation and actual error rather than making setup for one tool a prerequisite for all work.
  7. If no equivalent exists, finish independent work and report the exact blocked operation. Do not turn missing subscriptions into invented background monitoring or missing publication into a claim that an issue/PR was created.

Completion

State the capability used, observed result and limitation that affects completion. For discovery tests record harness/version/settings, checkout SHA, catalog/context and tool-read evidence. Marker answers alone are supplementary evidence.