Index of every page on this site: llms.txt
All skills
launchdarkly avatar

/should-flag-change

@f0ee110 official
Run it yourself

Decide whether a committed code change should ship behind a LaunchDarkly feature flag. Use when a developer asks whether a change should be behind a flag, when reviewing a diff or pull request, or when running in CI on a PR. Runs a fixed decision tree over the change and the code around it, with checked evidence, and emits a structured advisory recommendation. Run it on every change, including test-only, docs, dependency and already-flagged ones: those finish in a minute or two, and its verdict, not your own read of the diff, is the decision. Read-only: it never creates or modifies flags.

Use this Skill: https://skilld.dev/gh/launchdarkly/ai-tooling/should-flag-change

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencesFACTS.md

≈592 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Fact search

One question about this change was answered "unresolved", and the result depends on it: answered yes or no, the check would decide differently. The answer usually says what the evidence was missing -- a caller, a guard, a writer or reader, a setting, a route. That fact is often in the repository at the change's commit, outside the part of the code the evidence shows. Search for exactly that fact, and report what you find as quoted lines. Don't answer the question here, and don't look for anything else.

THE CHANGE

  • Repository: {CHECKOUT}. Read files at the change's commit only: git -C {CHECKOUT} show {HEAD}:<path>; search with git -C {CHECKOUT} grep -n <pattern> {HEAD} -- <paths>. The working tree may hold other work: don't read it.
  • The change's commit: {HEAD}. The version on main it is compared with: {BASE}. See the change with git -C {CHECKOUT} diff {BASE}...{HEAD}.
  • The evidence: {RUN}/evidence.txt.

THE QUESTION ({QUESTION_ID}) {QUESTION}

It is unresolved when: {UNRESOLVED_WHEN}

The answer given, and why it was unresolved: {ANSWER_EVIDENCE}

WHAT TO REPORT The lines at {HEAD} that show the missing fact, or show it isn't there: each one quoted exactly, with its path and line number, and a one-line claim of what it shows ("the only caller passes false", "this handler returns before the changed call when the account is new"). Report the lines that settle it, not everything you read: a few lines, at most 12. Each is checked mechanically -- its path must exist at {HEAD}, and the quoted text must match that line -- and a finding that doesn't match is dropped. Only verified lines are shown when the question is asked again, and the answer must still follow the question's procedure. If you can't find the fact, report no findings and say where you looked: that is a correct answer, and the question stays unresolved.

Read-only: don't modify the repository, create or change flags, or use the network.

Write ONLY this JSON to {RUN}/facts.json, then run python3 {SKILL_DIR}/ld-factory.pyz facts {RUN}:

{"question": "{QUESTION_ID}", "findings": [{"path": "path/at/head", "line": 12, "text": "the exact line", "claim": "one line: what this line shows"}], "not_found": false, "searched": "one or two sentences: what you looked for and where"}

THE QUESTION IN FULL, as it was asked:

{FULL_QUESTION}

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 alerttoday3 checks · Risk MEDIUM
  • Gen Agent Trust Hubtoday

    This skill utilizes a bundled executable that contains hidden Unicode characters, which could be used for malicious steganography, and it analyzes untrusted data from repositories and pull requests, making it susceptible to indirect prompt injection.

  • Sockettoday

    1 alert: gptSecurity

  • Snyktoday

    Risk: CRITICAL · 2 issues

Signed by skilld at f0ee110. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 days ago
metadata
{
  "author": "launchdarkly",
  "version": "0.5.3",
  "graph": "07355490e985"
}
Other metadata
compatibility
Advisory and read-only. Needs a git checkout with the change committed (shallow is fine; a --filter partial clone is filled in from its remote), a shell, git and Python 3.10+ (no packages). Reads LaunchDarkly flag state through your LaunchDarkly tools when available, and works without them. When it can't run (no shell, no checkout), it decides by judgment instead, from references/NO_CHECKOUT.md. Returns a structured verdict as a `recommend-flag` block.

README badge

README badge for launchdarkly/ai-tooling/should-flag-change