New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Follow PR

by DataDog in DataDog/datadog-agent

Monitor the current PR's GitLab pipeline to completion, then report success, auto-fix, or investigate a failure.

OfficialApache-2.0Auto-check passedDevOps & Cloud

Install Follow PR

skills CLI
$ npx skills add DataDog/datadog-agent --skill follow-pr -a claude-code

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

GitHub CLI
$ gh skill install DataDog/datadog-agent follow-pr --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/DataDog/datadog-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/follow-pr .claude/skills/follow-pr && 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
follow-pr
GitHub stars
3.8k
Token cost
~3.2k tokens
SKILL.md length
1,660 words
Files
3 (incl. scripts)
Skills in repo
35
Repo updated
First seen
Licence
Apache-2.0

At a glance

Monitor the current PR's GitLab pipeline to completion, then report success, auto-fix, or investigate a failure.

  • Works in 9 steps: Ensure correct environment → Determine the target → Resolve the autonomy policy → …
  • The user asks to follow
  • SKILL.md covers Step 0: Ensure correct…, Step 1: Determine the target, Step 2: Resolve the autonomy… and Step 3: Start monitoring, plus 7 more sections
  • Runs Python and Shell scripts from its folder; calls python3

What it does

Follow PR is an agent skill from DataDog/datadog-agent, published by the product's own GitHub organization. Monitor the current PR's GitLab pipeline to completion, then report success, auto-fix, or investigate a failure. Use when the user asks to follow, babysit, watch, or wait on a PR/pipeline, or just after pushing to / creating a PR.

Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `scripts/config.py` and `scripts/create_devenv.sh`).

It sits in DevOps & Cloud. It works with GitLab and Datadog. The repository describes itself as: Main repository for Datadog Agent. The licence is Apache-2.0.

When your agent uses it

  • The user asks to follow
  • Wait on a PR/pipeline
  • Just after pushing to / creating a PR

Example prompts

  • “/follow-pr”

Requirements

  • Python 3
  • A Bash shell

Workflow steps

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

  1. Ensure correct environment
  2. Determine the target
  3. Resolve the autonomy policy
  4. Start monitoring
  5. Interpret the output
  6. Act on the outcome
  7. follow-up on failures
  8. watch an unresolved incident
  9. decide whether to keep going

What it can do on your machine

Read from SKILL.md and the folder at commit a706f1a. 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

    Ships 2 files in scripts/ (Python and Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    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.

Context cost

Follow PR loads about 3.2k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 1,660 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~3.2k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from DataDog/datadog-agent at commit a706f1a, republished under its Apache-2.0 licence (© DataDog). 1,660 words, ~3,177 tokens.

Download SKILL.mdSave it as .claude/skills/follow-pr/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
follow-pr
description
Monitor the current PR's GitLab pipeline to completion, then report success, auto-fix, or investigate a failure. Use when the user asks to follow, babysit, watch, or wait on a PR/pipeline, or just after pushing to / creating a PR.
argument-hint
[<ref> | --pipeline <id>] [--fix-mode autofix|no-autofix|ask] [--max-fix-cycles N] [--policy TEXT]
model
sonnet

Follow PR

Watch the latest Gitlab CI pipeline for the current PR to a terminal state, report the outcome, and — for failures reliably caused by this PR — autonomously fix and push bounded ones under the resolved autonomy policy while investigating the rest locally.

Owning team: @DataDog/agent-devx

Step 0: Ensure correct environment

The appropriate tool for this usecase is ddgl, and more specifically ddgl attach. Check if ddgl is available - which ddgl. If so, move to Step 1. Otherwise, use a dev env as specified below.

Ensuring a dev env

First, check if you are running in a dev env: test -f /.started will exit 0 if so. If you are in an outdated devenv without ddgl, stop and notify the user to recreate his dev env. Otherwise, check for the existence of a dev env by using dda env dev show.

If there are existing dev envs:

  • Check if the current repo is properly mounted into that env (repos and extra_(mount|volume)_specs fields)
  • Check the current state of that dev env.

If the environment is already started and contains the right repo, move to the next step. Otherwise, create one by using ./scripts/create_devenv.sh, then use the environment ID printed by the script in subsequent commands.

Using a dev env

To run commands inside a dev env, use the following template:

bash
dda env dev run --id <dev-env-id> -- [command]

Watch out for space-splitting. For example:

bash
dda env dev run --id follow-pr-attach-7C2C42F6 -- ddgl attach --detail=normal --follow --plain

Step 1: Determine the target

If the user gave a ref, branch, or pipeline ID, pass it through (--ref <ref> or --pipeline <id>). Otherwise omit both — ddgl attach resolves the pipeline for the current branch on its own.

Step 2: Resolve the autonomy policy

Before starting the monitoring loop, resolve how this run should handle failures caused by the PR's own code:

bash
python3 .agents/skills/follow-pr/scripts/config.py resolve \
  [--mode <from --fix-mode arg>] [--max-fix-cycles <from arg>] [--policy <from arg>]

Pass through any --fix-mode, --max-fix-cycles, or policy text given in this invocation; otherwise the script falls back to environment variables, then worktree-local config, then global config, then its own default (autofix).

If the config ended up resolving using only the default values, suggest the user create a global/local config file with the settings he just chose for future invocations. Check the script contents to get the appropriate paths and formats.

  • Resolved mode is autofix or no-autofix: report the resolved mode, cycle budget, and whether a custom policy is active, then continue to Step 3.
  • Resolved mode is ask, or the script errors: ask the user directly, before monitoring starts, whether PR-caused failures this run should be fixed and pushed (autofix) or only investigated locally (no-autofix). Offer to persist the answer (worktree-local or global config) if they don't want to be asked again; otherwise use it for this run only.

Keep the resolved mode, cycle budget (default 2), and policy text in context — you'll pass them straight through as --mode/--max-fix-cycles/--policy to subskills that might need it.

Step 3: Start monitoring

All pipeline discovery, polling, follow/rebind, and timeout handling is covered by the internals of ddgl attach. Do not implement a second polling loop or persist monitoring state of your own.

Check whether you have a long-lived monitoring tool available, one that can run a command in the background and forward each stdout line as it arrives, without a timeout of its own (e.g. Claude Code's Monitor tool).

With such a tool: start it on

bash
ddgl attach --plain --follow --detail=full [--ref <ref> | --pipeline <id>]

and wait for a [FINAL] line — no --timeout needed.

Without one: run it in the foreground, bounded so the invocation cannot outlive your own harness timeout:

bash
ddgl attach --plain --follow --detail=full --timeout 600 [--ref <ref> | --pipeline <id>]

If the [FINAL] line reports a timeout (not a pipeline outcome), start an identical invocation again. This is safe: attach is stateless and each invocation begins with a fresh snapshot of the pipeline.

NOTE: If the pipeline is already terminal or does not exist when you start monitoring, the user might have just pushed and the pipeline is still waiting to be created. In this case, wait for 60 seconds and then re-attempt monitoring. The --follow argument will make sure ddgl attach always monitors the latest pipeline for the ref.

Step 4: Interpret the output

You may see:

  • [POLL] - rollup summary after a changed poll tick (jobs done/total, stage, failure count). Informational only.
  • [INFO] - an informational log from ddgl itself.
  • [PIPE] - a change in the pipeline status.
  • [JOB] - a job finished running and changed state.
  • [FINAL] - the terminal, authoritative outcome. Treat this line as the source of truth regardless of the command's exit code — it names the pipeline id, terminal status, and, on failure, the failed job names.

Step 5: Act on the outcome

  • Pipeline Success: stop monitoring and report the pipeline succeeded, using the final report template.
  • Some job failed, but the pipeline is still running: Most jobs on datadog-agent CI retry once automatically on any failure (.gitlab-ci.yml's default retry: max: 1, when: always), so a first-attempt failure alone isn't yet evidence of anything — GitLab will retry it once. A minority of jobs (most e2e, Windows, macOS — .retry_only_infra_failure) retry only on GitLab's infra-flavoured failure_reason values, so a script_failure there gets no automatic retry at all and is worth a closer look sooner. Unit test, linter, and build failures are less likely to be flakes regardless of policy. If you're unsure which policy a job is on: grep -rn '<job-name>' .gitlab/ .gitlab-ci.yml. Otherwise, ask the user whether to continue monitoring, or if this job failure is already a problem. In the latter case, move to Step 6.
  • Pipeline failed or canceled: Stop monitoring, report the status, and move to Step 6.
  • Timeout [FINAL]: re-invoke ddgl attach as in Step 3; this is not a true terminal outcome.
  • Unexpected error (from ddgl itself, or from the monitoring tool): report what happened. Do not attempt a recovery action.
Show full SKILL.md (728 more words)Show less

Step 6: follow-up on failures

Invoke /triage-ci-failure on the pipeline id from the [FINAL] line; it returns one CI triage result block per failed job.

Route each block by its Blame field — never by whether Incident happens to be none, since that value alone doesn't tell you the job wasn't PR-caused:

  • upstream: if Incident is active and still breaking, continue to Step 7 and wait it out. If stable or resolved, tell the user it's safe to rebase onto main and re-run — say plainly that stable is a weaker signal than resolved (the fix may still be in progress). If no incident is declared at all, say CI looks broken on main with nothing declared for it — worth surfacing loudly. Investigation ends here for that job.

  • infra or flake: report the verdict and its suggested action (typically a retry, citing the evidence /triage-ci-failure gave you). Investigation ends here for that job.

  • inconclusive: report the evidence and the two most likely readings. Investigation ends here for that job.

  • pr-code: collect every pr-code block from this pipeline. Before invoking the handler, check for repeats against every push made earlier in this same run:

    1. If any Failure signature matches one from an earlier push, that fix didn't work — tell /handle-pr-ci-failure explicitly that this failure already survived one autonomous attempt, so it treats that root cause as blocked rather than reattempting it as safe.
    2. If the fix-cycle budget is already fully consumed, tell /handle-pr-ci-failure it has no push budget left this run, so it should investigate every root cause without committing or pushing, same as no-autofix.
    3. Otherwise, nothing to flag — invoke it normally.

    Either way, invoke /handle-pr-ci-failure once with all of this pipeline's pr-code blocks together, passing --mode/--max-fix-cycles/--policy set to the values resolved in Step 2. Continue to Step 8 with its result.

Step 7: watch an unresolved incident

Only entered when /triage-ci-failure reported an incident that's still active and breaking for a failed job — this is the other half of watching a PR through: the pipeline is red because of something outside the PR, and it will stay red until that something changes.

Poll the incident on an interval (a few minutes is reasonable; don't busy-loop):

bash
.agents/skills/triage-ci-failure/scripts/incidents.py timeline <IR-nnnnn>

Watch for a state transition off active — to stable (a rollback or workaround has likely landed; rebasing is probably safe even if the root cause isn't fully fixed yet) or resolved/completed (the stronger signal). Once either happens, confirm recovery before telling the user to act — check that the job is passing again on main:

bash
pup cicd events aggregate \
  --query='ci_level:job @ci.pipeline.name:DataDog/datadog-agent @git.branch:main @ci.job.name:"<job name>"' \
  --compute=count --group-by='@ci.status' --from='2h'

Once main is clean, tell the user it's time to rebase onto main and re-run.

Step 8: decide whether to keep going

Read /handle-pr-ci-failure's result block:

  • Outcome: pushed: record its Failure signatures and increment the cycle count — Step 6 needs both for the repeat/budget checks on the next pipeline. Go back to Step 3 to watch the replacement pipeline at the Pushed SHA regardless of whether the budget is now exhausted; you still need to confirm this fix actually worked before you can stop. Return here through Step 6 once it finishes.
  • Outcome: committed-not-pushed: report the local commit and the remaining complex root cause(s) blocking a push using the final report template, then stop and let the user decide.
  • Outcome: needs-user or blocked: report the evidence and the specific question /handle-pr-ci-failure asked for using the final report template, then stop.

Every trip back through this loop re-runs /triage-ci-failure from scratch on the new pipeline — never reuse an earlier verdict for a different pipeline.

Final report

Whenever you stop for good — pipeline succeeded, an upstream/infra/flake verdict ended investigation, or /handle-pr-ci-failure returned anything other than a fresh pushed, close with this block instead of ad hoc prose:

text
Follow-PR report
Pipeline: <final pipeline id> (<SHA>)
Status: succeeded | failed | needs-user
Fixes pushed: <count> — <commit SHAs, or none>
Cycles consumed: <N>/<max_fix_cycles>
Remaining issues: <summary, or none>
User decision needed: <question, or none>
End follow-PR report

Examples

  • A missed rename breaks a lint job. /triage-ci-failure returns one pr-code block; /handle-pr-ci-failure classifies it safe, fixes it, verifies with dda inv linter.go, commits, and pushes. Step 8 sees Outcome: pushed (cycle 1 of 2), goes back to Step 3, and the replacement pipeline goes green.
  • A test fails intermittently under -race. /handle-pr-ci-failure classifies it complex, reproduces it locally, tries two distinct hypotheses, and stops with Outcome: needs-user and an uncommitted candidate diff — nothing is pushed.
  • A pushed fix's replacement pipeline fails again with the same Failure signature. Step 6 recognizes the repeat before invoking the handler, tells it not to reattempt a fix, and it investigates instead — no second push happens.

© DataDog, 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 2 other files (scripts) in .agents/skills/follow-pr of DataDog/datadog-agent.

  • SKILL.md
  • scripts/config.py
  • scripts/create_devenv.sh

Open the folder on GitHubat commit a706f1a

Compare with similar skills

Follow PR 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.

Follow PR compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Follow PR this skillDataDog/datadog-agent3.8k—~3.2kAutomated safety check: PassApache-2.0
Megatron-LM Base Image BumpNVIDIA/Megatron-LM18k—~2.8kAutomated safety check: PassApache-2.0
Megatron-LM CI/CD GuideNVIDIA/Megatron-LM18k—~1.8kAutomated safety check: PassApache-2.0
Setup Osworldxlang-ai/OSWorld-V23551 repos~2.6kAutomated safety check: NotesApache-2.0
Apm IntegrationsDataDog/dd-trace-js837—~3kAutomated safety check: PassCustom licence
Dd IdpDataDog/pup1k—~2kAutomated safety check: PassApache-2.0

Similar skills

  • Megatron-LM Base Image Bump

    NVIDIA/Megatron-LM

    Official

    Moves Megatron-LM CI to a newer NVIDIA PyTorch base image, updating both the GitHub and GitLab pins together and handling the CI follow-up.

    18k GitHub stars~2.8k tokensUpdated today
    DevOps & CloudAuto-check passed

  • Megatron-LM CI/CD Guide

    NVIDIA/Megatron-LM

    Official

    Explains Megatron-LM's CI pipeline, PR scope labels, triggering the internal GitLab CI with a dry run first, and investigating CI failures.

    18k GitHub stars~1.8k tokensUpdated today
    DevOps & CloudAuto-check passed

  • Setup Osworld

    xlang-ai/OSWorld-V2

    Provision and verify an OSWorld-V2 checkout after clone. An agent skill from xlang-ai/OSWorld-V2.

    355 GitHub starsUsed in 1 repo~2.6k tokens
    DevOps & CloudAuto-check: notes

  • Apm Integrations

    DataDog/dd-trace-js

    Official

    A skill your agent uses when adding, debugging, fixing, or modifying instrumentation and plugins for third-party libraries in dd-trace-js.

    837 GitHub stars~3k tokensUpdated today
    DevOps & CloudAuto-check passed

  • Dd Idp

    DataDog/pup

    Official

    Find, filter, count, and connect software, teams, engineering work and delivery, infrastructure, and operational or security records through Pup's read-only Datadog entity graph.

    1k GitHub stars~2k tokensUpdated today
    DevOps & CloudAuto-check passed

  • Datadog Data Source Generator

    DataDog/terraform-provider-datadog

    Official

    Generates a Datadog Terraform provider data source from an OpenAPI operation with tfgen and opens a review-ready GitHub PR with a risk scan and testing guide.

    468 GitHub stars~2.7k tokensUpdated today
    DevOps & CloudAuto-check passed

More from DataDog/datadog-agent

All 35 skills in this repo

  • Triage CI Failure

    DataDog/datadog-agent

    Official

    Classify a failed CI as either caused by an active incident, flakiness, or a true code regression.

    3.8k GitHub stars~2.3k tokensUpdated today
    Auto-check passed

  • Elicit

    DataDog/datadog-agent

    Official

    Run a structured discovery session to build an Allium specification through conversation.

    3.8k GitHub starsUsed in 1 repo~3.7k tokens
    Auto-check passed

  • Create Epic Recap

    DataDog/datadog-agent

    Official

    A skill your agent uses when an engineer or manager asks to recap, summarize, or post an update on a Jira Epic — a progress update for an in-progress Epic (how far along it is, what's shipped so…

    3.8k GitHub stars~5k tokensUpdated today
    Auto-check: notes

  • Explain Lading Config

    DataDog/datadog-agent

    Official

    Explains a lading.yaml config file from the regression test suite, using the lading Rust source as ground truth for field meanings and defaults.

    3.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Distill

    DataDog/datadog-agent

    Official

    Extract an Allium specification from an existing codebase. An agent skill from DataDog/datadog-agent.

    3.8k GitHub starsUsed in 1 repo~7k tokens
    Auto-check passed

  • Run E2E

    DataDog/datadog-agent

    Official

    Run one already-written new-e2e test locally and triage the setup failures that stop it — "run the containers e2e tests", "my e2e run fails before any test starts".

    3.8k GitHub stars~2.2k tokensUpdated today
    Auto-check: notes

Works with

Categories

Questions about Follow PR

What does Follow PR do?

Monitor the current PR's GitLab pipeline to completion, then report success, auto-fix, or investigate a failure. Follow PR is an agent skill from DataDog/datadog-agent, published by the product's own GitHub organization. Monitor the current PR's GitLab pipeline to completion, then report success, auto-fix, or investigate a failure.

When should I use Follow PR?

Follow PR fits situations like: the user asks to follow; wait on a PR/pipeline; just after pushing to / creating a PR.

How do I install Follow PR in Claude Code?

Run `npx skills add DataDog/datadog-agent --skill follow-pr -a claude-code`. Or copy the skill folder (.agents/skills/follow-pr in DataDog/datadog-agent) into .claude/skills/follow-pr in your project. Claude Code loads it when a task matches its description.

How do I install Follow PR in Codex?

Run `npx skills add DataDog/datadog-agent --skill follow-pr -a codex`. Or copy the skill folder (.agents/skills/follow-pr in DataDog/datadog-agent) into .agents/skills/follow-pr in your project. Codex loads it when a task matches its description.

Can I use Follow PR 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 DataDog/datadog-agent --skill follow-pr -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/follow-pr, .gemini/skills/follow-pr, .github/skills/follow-pr and .opencode/skills/follow-pr in your project.

What does Follow PR need to run?

Going by SKILL.md and its folder, Follow PR needs Python and a shell for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3; A Bash shell.

Does Follow PR 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 Follow PR 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Follow PR use?

Follow PR 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 Follow PR use?

About 3.2k tokens (SKILL.md is roughly 13k 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 Follow PR?

Skills that share tags, products or a category with Follow PR: Megatron-LM Base Image Bump (NVIDIA/Megatron-LM, 18k stars), Megatron-LM CI/CD Guide (NVIDIA/Megatron-LM, 18k stars), Setup Osworld (xlang-ai/OSWorld-V2, 355 stars) and Apm Integrations (DataDog/dd-trace-js, 837 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Follow PR?

DataDog (a GitHub organization, an official publisher) maintains it in DataDog/datadog-agent, which has 3,759 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on October 9, 2026.

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