Agent skill

Qv Devops Why My PR Not

by tetherto in tetherto/qvac

Diagnose why CI checks are not running on a PR and/or why a PR cannot be merged by comparing live PR state with current labels, CODEOWNERS, fork trust, and approval configuration.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Qv Devops Why My PR Not

skills CLI
$ npx skills add tetherto/qvac --skill qv-devops-why-my-pr-not -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install tetherto/qvac qv-devops-why-my-pr-not --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/tetherto/qvac.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/qv-devops-why-my-pr-not .claude/skills/qv-devops-why-my-pr-not && rm -rf skills-src

Use ~/.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/

Facts

Skill name
qv-devops-why-my-pr-not
GitHub stars
683
Token cost
~4.4k tokens
SKILL.md length
1,900 words
Files
2
Skills in repo
50
Repo updated
First seen
Licence
Apache-2.0

At a glance

Diagnose why CI checks are not running on a PR and/or why a PR cannot be merged by comparing live PR state with current labels, CODEOWNERS, fork trust, and approval configuration.

  • Works in 8 steps: Parse and validate the PR identifier → Read the canonical docs (once per… → Fetch live PR state → …
  • A developer asks why checks are missing
  • SKILL.md covers When to use this skill, Inputs, Prerequisites and Safety rules, plus 4 more sections
  • Calls gh and git; needs PAT_TOKEN

What it does

Qv Devops Why My PR Not is an agent skill from tetherto/qvac. Diagnose why CI checks are not running on a PR and/or why a PR cannot be merged by comparing live PR state with current labels, CODEOWNERS, fork trust, and approval configuration. Read-only by default. Use when a developer asks why checks are missing, why a PR cannot merge, or invokes /qv-devops-why-my-pr-not with a PR URL.

Its SKILL.md is about 4.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in AI & LLM Engineering. It works with GitHub. The repository describes itself as: Open-source local AI SDK - run AI on-device with no cloud, no API keys. Supports GGUF, RAG, image, music, and video generation, speech-to-text, P2P inference, and more… The licence is Apache-2.0.

When your agent uses it

  • A developer asks why checks are missing
  • Why a PR cannot merge
  • Invokes /qv-devops-why-my-pr-not with a PR URL

Example prompts

  • “/qv-devops-why-my-pr-not”

Requirements

  • A credential in PAT_TOKEN

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Parse and validate the PR identifier
  2. Read the canonical docs (once per session, cached)
  3. Fetch live PR state
  4. Run the CI-not-running diagnosis (--ci / --both)
  5. Run the merge-blocked diagnosis (--merge / --both)
  6. Render the report
  7. Plan-then-apply mutations (only if user opts in)
  8. Stop conditions (fail-stop)

What it can do on your machine

Read from SKILL.md and the folder at commit f874b3a. 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

    Shell commands in SKILL.md call:

    • gh
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • PAT_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Qv Devops Why My PR Not loads about 4.4k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 1,900 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~87
When it runs · the whole SKILL.md, loaded when a task matches
~4.4k

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 tetherto/qvac at commit f874b3a, republished under its Apache-2.0 licence (© tetherto). 1,900 words, ~4,358 tokens.

Download SKILL.mdSave it as .claude/skills/qv-devops-why-my-pr-not/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
qv-devops-why-my-pr-not
description
Diagnose why CI checks are not running on a PR and/or why a PR cannot be merged by comparing live PR state with current labels, CODEOWNERS, fork trust, and approval configuration. Read-only by default. Use when a developer asks why checks are missing, why a PR cannot merge, or invokes /qv-devops-why-my-pr-not with a PR URL.
disable-model-invocation
true

devops-why-my-pr-not

Self-service triage for the two most common DevOps support questions:

  1. "Why aren't my CI checks running?" — use the canonical CI label and gate docs below; they define which labels, trust rules, and fork restrictions control job execution.
  2. "Why can't I merge?" — use the current approval workflow, CODEOWNERS, and branch-protection state; they define required approvals and merge conditions.

The skill cross-references the live PR state (via gh) against the canonical repo docs that describe the rules:

The docs are the source of truth. The skill quotes them; it does not re-derive their rules.

When to use this skill

Use when:

  • A developer asks "why aren't my checks running on PR #N?"
  • A developer asks "why can't I merge PR #N?" / "what's blocking my PR?"
  • A reviewer asks "what does this PR still need before I can merge it?"
  • User invokes /qv-devops-why-my-pr-not <PR URL>

Do NOT use when:

Inputs

  • Required: PR URL or <owner>/<repo>#<num> shorthand (defaults owner/repo to tetherto/qvac if only #<num> is given).
  • Optional: focus hint — --ci, --merge, or --both (default --both).

If the PR identifier is missing, ask once. Nothing else to ask up-front.

Prerequisites

  • gh CLI installed and authenticated (gh auth status). The token needs repo scope to read PR metadata, checks, and reviews on tetherto/qvac.
  • read:org is not required by the skill itself. If privileged fork jobs fail while recording qvac/fork-verified, check fork-approval logs — the gate job uses github.token with statuses: write (not PAT_TOKEN).

The skill does not require a checked-out worktree. All inspection is via gh.

Safety rules

This skill follows the repository working agreement: read-only by default, with each remote mutation requiring explicit user authorization.

  • Read-only with respect to the user's local working tree. No git switch, git checkout, git reset, git restore, git stash, git pull, git merge, git rebase, git cherry-pick, git clean, gh pr checkout, or any write inside the user's working tree.
  • Read-only with respect to the PR's GitHub state by default. No gh pr edit, no gh api ... -X POST/PATCH/PUT/DELETE, no gh pr comment, no gh pr review without explicit user confirmation per call.
  • Mutations are plan-then-apply. When the diagnosis suggests a fix that the user could perform (apply a label, post /review, request re-review from a teammate, rebase to drop a merge conflict), print the exact gh command, wait for the user to type "yes" / "go" / "apply", then execute. A blanket "do everything" is not accepted — confirm per command.
  • Never approve the fork-ci environment on the user's behalf. That gate is intentionally not self-service. The skill may suggest who to ask (merge/release team), never click approve for them.

Efficiency rules

Cap at 6 shell calls for a normal diagnosis. Cache fetched data once per invocation under /tmp/why-pr-<num>-<short-sha>.json so repeat queries within the same session do not re-hit GitHub.

CallPurpose
1gh pr view <num> --json number,title,state,isDraft,labels,author,baseRefName,headRefName,headRefOid,headRepositoryOwner,headRepository,mergeable,mergeStateStatus,reviewDecision,reviews,statusCheckRollup,latestReviews
2gh pr checks <num> --json name,state,conclusion,workflow,link (or gh api .../check-runs?head_sha=<sha> if gh pr checks is unavailable)
3gh api repos/<owner>/<repo>/commits/<sha>/status when commit statuses are not present in the PR check rollup
4gh api repos/<owner>/<repo>/branches/<base>/protection (only if the user explicitly opts into branch-protection inspection — needs admin/maintain)
5(reserved for plan-then-apply mutation, e.g. gh pr edit --add-label)
6(verification re-read of gh pr view after a mutation)

If a single call covers multiple needs (e.g. gh pr view --json already lists labels and reviews), do not re-fetch.

Workflow

1. Parse and validate the PR identifier

Accept any of:

  • https://github.com/tetherto/qvac/pull/12345
  • tetherto/qvac#12345
  • #12345 → resolves to tetherto/qvac#12345
  • bare 12345 → resolves to tetherto/qvac#12345

Extract <owner>, <repo>, <num>. Reject if any are missing. Print the resolved canonical URL.

2. Read the canonical docs (once per session, cached)

Before fetching the PR, ensure you've read these in this turn (or already have them in context):

These are short. Read them in full. Quote them in findings, do not paraphrase from memory — the rules drift over time and the doc is authoritative.

Read check-approvals.yml when an approval finding is triggered rather than relying on remembered thresholds.

For pod ownership, read .github/teams/devops.json / .github/teams/sdk.json on demand when computing "who can approve fork-ci" or "who is in your CODEOWNERS path."

3. Fetch live PR state

Single call:

bash
gh pr view <num> -R <owner>/<repo> --json number,title,state,isDraft,labels,author,baseRefName,headRefName,headRefOid,headRepositoryOwner,headRepository,mergeable,mergeStateStatus,reviewDecision,reviews,statusCheckRollup,latestReviews,files

Cache the JSON to /tmp/why-pr-<num>-<short-sha>.json. Pull headRefOid for any subsequent commits/<sha>/... calls.

Then fetch checks (one call):

bash
gh pr checks <num> -R <owner>/<repo> --json name,state,conclusion,workflow,link

If a required commit status is not represented in the check rollup, use one more call:

bash
gh api "repos/<owner>/<repo>/commits/<headRefOid>/status"
4. Run the CI-not-running diagnosis (--ci / --both)

Walk down this checklist in order. Stop at the first match per dimension; print all matches across the checklist.

#Symptom (from PR JSON / checks JSON)DiagnosisCite
C1PR isDraft == true AND a workflow has pull_request: types: [opened, synchronize, reopened] (default)Draft PRs do not fire pull_request events for ready_for_review excluded triggers. Mark the PR as ready or push a new commit.GitHub default pull_request event semantics
C2Workflow runs are present but jobs gated on needs: fork-approval are WAITING / pending environment approvalExternal fork PR: a merge/release-team member must approve the fork-ci environment for this run (GitHub UI → pending deployment). Each new push re-prompts.docs/ci/LABELS.md (fork-ci)
C3Same jobs SKIPPED after approval, AND qvac/fork-verified commit status is missing or not success for headRefOidfork-approval should record qvac/fork-verified on the head SHA after env approval via github.token (statuses: write). If missing, check fork-approval job logs. Self-hosted pull_request jobs (e.g. pr-test-inference-addon-cpp*) read this status, not labels.docs/ci/LABELS.md
C4PR is from a fork AND privileged jobs ran without env approval (should not happen post label-gate retirement)Report to DevOps — privileged fork jobs must needs: fork-approval.ci-trust-policy.test.mjs
C5PR is from a fork (headRepositoryOwner.login != tetherto) AND only secret-bearing jobs are missingExpected until fork-ci is approved for the current SHA. Unprivileged pull_request fork jobs stay read-only (no secrets).docs/ci/LABELS.md
C6An expensive validation workflow is missing AND PR is an external fork AND fork-ci not yet approved for current SHAAsk merge/release team to approve the pending fork-ci deployment on the latest workflow run. Do not recommend the retired verified label.docs/ci/LABELS.md
C7pr-checks-sdk-pod.yml jobs are skipped AND PR touches packages/sdk/ from a fork AND safe-to-test is missingSDK pod's check-running gate. Reviewer must apply safe-to-test after auditing the diff.LABELS.md § safe-to-test
C8E2E suite did not run AND PR touches SDK AND neither test-e2e-smoke nor test-e2e-full is presentSDK E2E is opt-in via these labels. Apply the smoke variant for normal PR feedback.LABELS.md § test-e2e-smoke / test-e2e-full
C9A workflow run is FAILED in fork-approval (red, not waiting)Hard misconfiguration — usually missing statuses: write on the gate job or failure recording qvac/fork-verified. DevOps issue.fork-approval job logs
C10Required check is in IN_PROGRESS state with no failure; user is just impatientWait. Or surface the slowest job's link.gh pr checks output

For each match, print what the rule says (one short quote pulled from the cite) plus what the user should do (a single concrete action).

Show full SKILL.md (735 more words)Show less
5. Run the merge-blocked diagnosis (--merge / --both)

Walk this checklist in order, same rule: stop at first match per dimension, print all matches.

#SymptomDiagnosisCite
M1mergeable: "CONFLICTING" or mergeStateStatus: "DIRTY"Merge conflicts with <baseRefName>. Rebase or merge base into branch.gh pr view --json mergeable,mergeStateStatus
M2state: "CLOSED" or state: "MERGED"PR is not open. Re-open it (if closed) or there's nothing to merge (if merged).n/a
M3isDraft: trueDraft PRs cannot be merged. Mark ready for review.n/a
M4reviewDecision: "REVIEW_REQUIRED" AND CODEOWNERS approval not presentThe CODEOWNERS team(s) for the touched paths must approve. Identify the team via the file's owners line; suggest 1-2 names from the team JSON..github/CODEOWNERS, .github/teams/<pod>.json
M5reviewDecision: "CHANGES_REQUESTED"A review requested changes. Resolve the requested changes and either re-request review or have the reviewer dismiss.n/a
M6Check Approvals failed or its latest comment reports missing approvalsRead the workflow and bot output for the current deficit; do not infer historical tier rules..github/workflows/check-approvals.yml
M7A required check (per statusCheckRollup) is FAILEDThe required check must pass. Link to the failed run; if it's flake, re-run; if it's a real failure, fix.gh pr checks
M8A required check is missing entirely from statusCheckRollupEither the gating workflow is skipping/waiting (loop back to the CI section — usually fork-ci pending) OR a required check name in branch protection no longer matches a real job (DevOps issue).branch-protection ruleset
M9Base branch protection updated mid-PR (new required check added)Push an empty commit (git commit --allow-empty) to re-trigger checks against the new ruleset.n/a
M10All checks green, all approvals satisfied, mergeable: "MERGEABLE", mergeStateStatus: "CLEAN"Nothing is blocking. Print "ready to merge" and the merge command the user can run themselves (do not run it).n/a

When suggesting reviewers, use current CODEOWNERS and team files for the touched paths. Do not infer reviewers from an obsolete tier model.

6. Render the report

Print one consolidated report. Two top-level sections (omit a section if the user asked for a single dimension).

PR: <owner>/<repo>#<num> — <title>
Author: @<login>   Base: <baseRefName>   Head: <headRefName>@<short-sha>
State: <state> | Draft: <isDraft> | Mergeable: <mergeable>/<mergeStateStatus> | Review: <reviewDecision>
Labels: <comma-separated>

── CI: are checks running? ──────────────────────────────────────────
[<symbol>] <C#> <one-line summary>
   Rule:    <one-line quote from cited doc>
   Action:  <one concrete next step>
   Cite:    <relative link>

[<symbol>] <C#> ...

(or "✓ All expected checks are running.")

── Merge: can it land? ───────────────────────────────────────────────
[<symbol>] <M#> <one-line summary>
   Rule:    <one-line quote from cited doc>
   Action:  <one concrete next step>
   Cite:    <relative link>

[<symbol>] <M#> ...

(or "✓ All merge requirements satisfied.")

── Suggested next actions ───────────────────────────────────────────
1. <concrete action> — <user-friendly description>
2. ...

Use simple symbols: [!] for blocking, [~] for soft (e.g. waiting), [i] for informational, [✓] for satisfied. No emojis (per repo convention).

7. Plan-then-apply mutations (only if user opts in)

The skill MAY propose at most one mutation per finding. Each proposal prints the exact command and waits for explicit confirmation. Examples:

  • Apply safe-to-test (only after the user confirms they have audited the fork's diff):
    bash
    gh pr edit <num> -R <owner>/<repo> --add-label safe-to-test
  • Re-trigger approval bot:
    bash
    gh pr comment <num> -R <owner>/<repo> --body "/review"
  • Request re-review from a specific approver:
    bash
    gh api -X POST repos/<owner>/<repo>/pulls/<num>/requested_reviewers \
      -f reviewers='["<login>"]'
  • Mark draft PR as ready for review:
    bash
    gh pr ready <num> -R <owner>/<repo>

Never propose approving the fork-ci environment on the user's own PR. If privileged fork jobs are waiting, the suggestion is "ask a merge/release-team member to approve the pending fork-ci deployment" — not "I'll approve it for you."

After any mutation, re-run step 3 (single gh pr view) and re-render only the section(s) that changed. Print one verification line: Verified: <label X> now present | reviewers <Y, Z> requested | etc.

8. Stop conditions (fail-stop)

Stop and report (do not guess) when:

  • gh auth status reports unauthenticated → tell the user to run gh auth login.
  • The PR JSON returns 404 → wrong number / wrong repo / private repo.
  • The skill needs to read branch protection but the user lacks permission (HTTP 403) → state the limitation; the merge-blocked diagnosis falls back to "what we can see from PR state alone".
  • The diagnosis returns zero findings AND the user clearly believes something is broken → say so; offer to dump the raw PR JSON for the user to inspect.

Quality checklist

Before printing the final report, verify:

  • Each finding cites a real rule from docs/ci/LABELS.md, docs/ci/TEAMS.md, approval-check-worker.yml, or CODEOWNERS — not from memory.
  • Each finding has both a "Rule" (one-line quote) and an "Action" (one concrete step).
  • Suggested approvers come from current CODEOWNERS and team configuration, not memory.
  • No mutation has been executed without an explicit per-command confirmation.
  • fork-ci approval was never proposed for self-application.
  • Total gh shell calls ≤ 6 for a read-only diagnosis (≤ 8 if a mutation + verification was performed).

References

© tetherto, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/qv-devops-why-my-pr-not of tetherto/qvac.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit f874b3a

Compare with similar skills

Qv Devops Why My PR Not 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.

Qv Devops Why My PR Not compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Qv Devops Why My PR Not this skilltetherto/qvac683—~4.4kAutomated safety check: PassApache-2.0
Esmfold2JimLiu/science-skills2274 repos~2.5kAutomated safety check: PassApache-2.0
Create Simple Promptpnp/copilot-prompts892—~2.6kAutomated safety check: PassMIT
Issue Workflow Guardrailkxn/codex-remote-feishu329—~1.3kAutomated safety check: PassNone
Gptqmodel Tokenizer NormalizationModelCloud/GPTQModel1.3k—~1.1kAutomated safety check: PassCustom licence
ML Failure DebuggerLeeroo-AI/superml195—~9.5kAutomated safety check: PassApache-2.0

Similar skills

  • Esmfold2

    JimLiu/science-skills

    Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.

    227 GitHub starsUsed in 4 repos~2.5k tokens
    AI & LLM EngineeringAuto-check passed
  • Create Simple Prompt

    pnp/copilot-prompts

    This skill should be used when the user asks to "create a new prompt sample", "add a new prompt sample", "scaffold a new prompt sample", "create a prompt contribution", "add a prompt", or needs to…

    892 GitHub stars~2.6k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed
  • Issue Workflow Guardrail

    kxn/codex-remote-feishu

    A skill your agent uses when handling a GitHub issue in this repository: raw issue shaping, implementability reassessment, fast/full classification, parent/child orchestration, execution snapshots…

    329 GitHub stars~1.3k tokensUpdated 8 days ago
    AI & LLM EngineeringAuto-check passed
  • Diagnose and correct GPT-QModel tokenizer initialization, tokenization normalization, special-token handling, prompt rendering, and chat-template problems.

    1.3k GitHub stars~1.1k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • ML Failure Debugger

    Leeroo-AI/superml

    Diagnoses failing ML and AI work, such as OOM, NaN, divergence, crashes, slow throughput, wrong outputs and dependency conflicts, with every claim backed by documentation citations.

    195 GitHub stars~9.5k tokensUpdated 6 mo ago
    AI & LLM EngineeringAuto-check passed
  • Fix Art Issues

    OpenPipe/ART

    Fix a GitHub issue on OpenPipe/ART and open a PR. An agent skill from OpenPipe/ART.

    11k GitHub stars~840 tokensUpdated today
    AI & LLM EngineeringAuto-check: notes

More from tetherto/qvac

All 50 skills in this repo
  • Creates a Solutions page in the QVAC documentation website from a real use case, generalizing the case into reusable guidance and registering the page in the site navigation.

    683 GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • Qv Docs Update

    tetherto/qvac

    Updates the docs website after a change to the SDK or CLI. An agent skill from tetherto/qvac.

    683 GitHub stars~11k tokensUpdated today
    Auto-check passed
  • Qv Agent Stack Sync

    tetherto/qvac

    Plan and prepare the QVAC agent-stack release cascade across @qvac/inference, @qvac/sdk, @qvac/cli, @qvac/ai-sdk-provider, @qvac/opencode-plugin, and @qvac/openclaw-plugin.

    683 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Run the deterministic code-quality audit, turn related findings into contextual remediation groups, prepare approval-gated Asana proposals, reconcile recurring runs, or configure twice-monthly…

    683 GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Review C++ changes for string parameter and call-site efficiency conventions (std::stringview, std::string&&, const std::string&, const char, and TransparentStringMap lookup).

    683 GitHub stars~702 tokensUpdated today
    Auto-check passed
  • Qv Addon Changelog

    tetherto/qvac

    Generate changelog entries for a target add-on package. An agent skill from tetherto/qvac.

    683 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

Works with

Questions about Qv Devops Why My PR Not

What does Qv Devops Why My PR Not do?

Diagnose why CI checks are not running on a PR and/or why a PR cannot be merged by comparing live PR state with current labels, CODEOWNERS, fork trust, and approval configuration. Qv Devops Why My PR Not is an agent skill from tetherto/qvac. Diagnose why CI checks are not running on a PR and/or why a PR cannot be merged by comparing live PR state with current labels, CODEOWNERS, fork trust, and approval configuration.

When should I use Qv Devops Why My PR Not?

Qv Devops Why My PR Not fits situations like: A developer asks why checks are missing; why a PR cannot merge; invokes /qv-devops-why-my-pr-not with a PR URL.

How do I install Qv Devops Why My PR Not in Claude Code?

Run `npx skills add tetherto/qvac --skill qv-devops-why-my-pr-not -a claude-code`. Or copy the skill folder (.agents/skills/qv-devops-why-my-pr-not in tetherto/qvac) into .claude/skills/qv-devops-why-my-pr-not in your project. Claude Code loads it when a task matches its description.

How do I install Qv Devops Why My PR Not in Codex?

Run `npx skills add tetherto/qvac --skill qv-devops-why-my-pr-not -a codex`. Or copy the skill folder (.agents/skills/qv-devops-why-my-pr-not in tetherto/qvac) into .agents/skills/qv-devops-why-my-pr-not in your project. Codex loads it when a task matches its description.

Can I use Qv Devops Why My PR Not 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 tetherto/qvac --skill qv-devops-why-my-pr-not -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/qv-devops-why-my-pr-not, .gemini/skills/qv-devops-why-my-pr-not, .github/skills/qv-devops-why-my-pr-not and .opencode/skills/qv-devops-why-my-pr-not in your project.

What does Qv Devops Why My PR Not need to run?

Going by SKILL.md and its folder, Qv Devops Why My PR Not needs the command-line tools its instructions call (gh and git) and credentials named PAT_TOKEN. Our summary lists: A credential in PAT_TOKEN.

Does Qv Devops Why My PR Not access the network?

SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Qv Devops Why My PR Not 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 Qv Devops Why My PR Not use?

Qv Devops Why My PR Not is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Qv Devops Why My PR Not use?

About 4.4k tokens (SKILL.md is roughly 17k 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 Qv Devops Why My PR Not?

Skills that share tags, products or a category with Qv Devops Why My PR Not: Esmfold2 (JimLiu/science-skills, 227 stars), Create Simple Prompt (pnp/copilot-prompts, 892 stars), Issue Workflow Guardrail (kxn/codex-remote-feishu, 329 stars) and Gptqmodel Tokenizer Normalization (ModelCloud/GPTQModel, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Qv Devops Why My PR Not?

tetherto (a GitHub organization) maintains it in tetherto/qvac, which has 683 GitHub stars. The repository holds 50 skills in this directory. The repository was last updated on October 9, 2026.

Source: tetherto/qvac on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.