kevinveenbirkenbach/skills
1
0 Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity

feat(triage): coordinate every cluster and fix it through its own funnel

Browse Source 
Each failure cluster is first coordinated with the agents on related branches through the coordinate skill, so a fix that already exists elsewhere is taken instead of duplicated. Every claimed cluster then goes to the funnel skill: one agent in its own worktree, branched from the exact current HEAD, with that cluster as its only concern, the cluster's artifact paths in its brief and a hard time cap. Dialectic, the shared-versus-hidden split and the fix run inside that sidetree. A fix reaches the main line only at 90 % fix confidence and under 5 % break risk after independent review; below that the cluster ends as a proposal. The per-job verdict now names the sidetree branch and the funnel verdict. Steps are renumbered; observe's reference to step 1 is unchanged.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Kevin Veen-BirkenbachandClaude Opus 5.5 committed 2026-10-30 14:55:04 +01:00
1 parent 616f9f1b58
commit 63eedba3e2
1 file changed
+34 -14
Download Patch File Download Diff File Expand all files Collapse all files
skills/triage/SKILL.md
+34 -14
View File
@@ -3,8 +3,10 @@ name: triage
description: > description: >
Triage a failing CI run, pipeline, or job set to a verified root cause and a Triage a failing CI run, pipeline, or job set to a verified root cause and a
real fix. Trigger when a build, test, or deploy pipeline has one or more failed real fix. Trigger when a build, test, or deploy pipeline has one or more failed
jobs. Applies the dialectic skill to every failing job independently. Portable jobs. Applies the dialectic skill to every failing job independently, the
across projects. coordinate skill to every failure cluster, and the funnel skill to every
cluster, so each cluster is fixed in its own worktree. Portable across
projects.
--- ---
Drive a red pipeline to green by root cause, not by guesswork. Treat every Drive a red pipeline to green by root cause, not by guesswork. Treat every
@@ -34,7 +36,12 @@ root cause is proven.
actual failing line, not by job name. Jobs whose messages differ in anything actual failing line, not by job name. Jobs whose messages differ in anything
but the interpolated identifiers (host, app, port, path) belong in separate but the interpolated identifiers (host, app, port, path) belong in separate
clusters. clusters.
3. **Download artifacts per cluster.** Use the `ci-artifacts` skill for the 3. **Coordinate every cluster.** Invoke the `coordinate` skill for each cluster
before fixing it: tell the agents whose branches this one inherits from or
passes its commits on to which run failed and on which line, ask whether
someone already fixes it, and either take their fix or claim yours. Keep
investigating while you wait for answers.
4. **Download artifacts per cluster.** Use the `ci-artifacts` skill for the
mechanics — it covers per-job logs while a run is still in progress, which mechanics — it covers per-job logs while a run is still in progress, which
bundle to pull, and the grep hygiene that keeps a false positive from bundle to pull, and the grep hygiene that keeps a false positive from
becoming a root cause. For each cluster, fetch every artifact of becoming a root cause. For each cluster, fetch every artifact of
@@ -45,21 +52,33 @@ root cause is proven.
exception and the state dumps are inside the artifact. Do this even when the exception and the state dumps are inside the artifact. Do this even when the
log looks conclusive, because a log that explains the symptom rarely log looks conclusive, because a log that explains the symptom rarely
explains the cause. explains the cause.
4. **Dialectic per cluster.** For EACH cluster, invoke the `dialectic` skill: 5. **One funnel per cluster.** Hand every cluster you claimed in step 3 to the
`funnel` skill: one agent per cluster, working in its own worktree on its own
branch created from the exact current HEAD, with that cluster as its only
concern, the artifact paths of step 4 in its brief and a hard time cap. Steps 6 to 8 run inside that sidetree, so no
cluster's edits land under another cluster's work or under a running gate or
deploy. Run clusters in parallel only when their fixes touch different files
and the machine has room. A split cluster (step 7) gets a funnel of its own.
6. **Dialectic per cluster.** For EACH cluster, invoke the `dialectic` skill:
form a thesis about the root cause from evidence (the job log, its artifacts, form a thesis about the root cause from evidence (the job log, its artifacts,
the code at the run's commit, git history), attack it with independent the code at the run's commit, git history), attack it with independent
skeptics, and iterate to a ~99% thesis. The clusters are independent, so run skeptics, and iterate to a ~99% thesis.
their investigations in parallel where the tooling allows. 7. **Distinguish shared vs hidden causes.** A cluster is a hypothesis, not a
5. **Distinguish shared vs hidden causes.** A cluster is a hypothesis, not a
proof: if the dialectic shows one cluster splitting into two causes, split it. proof: if the dialectic shows one cluster splitting into two causes, split it.
When a job hides a second failure behind the first, keep going until the job When a job hides a second failure behind the first, keep going until the job
is actually green, not just past the first error. is actually green, not just past the first error.
6. **Fix at the root.** Apply the real fix in the repository for each proven root 8. **Fix at the root, through the funnel.** Apply the real fix for each proven
cause. Never mask a failure — no retry-until-pass, no disabling the check, no root cause in the cluster's sidetree, with a test and a negative control as
soft-skip. If a failure is genuinely external (upstream outage, flaky infra), the `funnel` skill demands. The fix enters the main line only at the funnel's
confirm that with evidence and surface it honestly instead of fixing around bar (at least 90 % fix confidence, under 5 % break risk) after its
it. independent review; below the bar the cluster ends as a proposal for the
7. **Follow the run.** While the run is still in progress, re-check it operator, never as a merge. Never mask a failure: no retry-until-pass, no
disabling the check, no soft-skip. If a failure is genuinely external
(upstream outage, flaky infra), confirm that with evidence and surface it
honestly instead of fixing around it. Report every fix, every proposal, and
every abandoned attempt to the same agents through the `coordinate` skill,
then remove the sidetree.
9. **Follow the run.** While the run is still in progress, re-check it
periodically and triage each newly failed job as it appears. The run is done periodically and triage each newly failed job as it appears. The run is done
only when it has finished and every failure has a verified fix. only when it has finished and every failure has a verified fix.
@@ -82,4 +101,5 @@ root cause is proven.
alone: the run cannot contain a fix that landed after it, so looking there alone: the run cannot contain a fix that landed after it, so looking there
can only ever confirm the failure. Name the commit that carries the fix. can only ever confirm the failure. Name the commit that carries the fix.
- Report a per-job verdict: root cause, the artifact path and line that prove - Report a per-job verdict: root cause, the artifact path and line that prove
it, and the fix. A verdict that cites only the job log has not finished step 3. it, the fix, the cluster's sidetree branch, and the funnel verdict (merged or
proposal). A verdict that cites only the job log has not finished step 4.