agentleFS
SimonKreis-RichardSimonKreis-Richard/oracle-fusion-agentic-toolkit/skills/triage/SKILL.md

triage

Skill0 starsChanged 51 days agoMITView on GitHub

Root-cause triage of an Oracle HCM Jira ticket, ending in the steps you run yourself and the message you send

  • Installs packages

190 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use writing-beats, setup-matt-pocock-skills and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • LesaniSkill

    writing-beats

    Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.

    Also in 74 projects that use this

  • GoogleSkill

    setup-matt-pocock-skills

    Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

    Also in 182 projects that use this

  • SethGammonSkill

    ascii-diagram

    Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.

    Also in 4 projects that use this

  • simo97Skill

    migrate-to-shoehorn

    Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.

    Also in 74 projects that use this

  • LesaniSkill

    writing-shape

    Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.

    Also in 70 projects that use this

  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 47 projects that use this

  • +1 more from Lesani

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 6 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 179 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run a full root-cause triage of Jira ticket $ARGUMENTS.

    line 8
  2. Very specific:

    Check whether tickets/$ARGUMENTS/ticket.md already exists.

    line 15
  3. Distinctive:

    If it does, use it as is.

    line 17
  4. Distinctive:

    If it does not, run the ingestion:

    line 18
  5. Distinctive:

    If the ingestion fails on authentication, show the credential instructions the script printed, then stop.

    line 26
  6. Very specific:

    Read tickets/$ARGUMENTS/ticket.md in full, then open every image in tickets/$ARGUMENTS/images/.

    line 32
  7. Very specific:

    Follow the jira-ticket-ingestion skill.

    line 34
  8. Distinctive:

    Do not write a single hypothesis before every image has been viewed.

    line 36
  9. Very specific:

    Follow the hcm-debugging skill, all of it, in order:

    line 40
  10. Distinctive:

    Read the scope section of the skill before step 5.

    line 58
  11. Very specific:

    Write the report to tickets/$ARGUMENTS/triage-report.md following the template in the hcm-debugging skill, then show it in the conversation.

    line 64

“Common” is measured: kept by at least 6 in 10 of the 179 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Run a full root-cause triage of Jira ticket $ARGUMENTS.

Jira is read-only for the whole of this command. Never issue anything other than GET against Jira, and never write anything back to the ticket.

1. Get the dossier

Check whether tickets/$ARGUMENTS/ticket.md already exists.

  • If it does, use it as is.
  • If it does not, run the ingestion:

    node dist/jira_ingest.js $ARGUMENTS

    Build first with npm install && npm run build if dist/jira_ingest.js is missing.

If the ingestion fails on authentication, show the credential instructions the script printed, then stop. Do not analyse a ticket you could not fetch, and do not ask the user for their token in the conversation.

2. Read everything

Read tickets/$ARGUMENTS/ticket.md in full, then open every image in tickets/$ARGUMENTS/images/. The exact error text, the page state and the visible configuration values usually live in the screenshots. Follow the jira-ticket-ingestion skill.

Do not write a single hypothesis before every image has been viewed.

3. Apply the debugging heuristic

Follow the hcm-debugging skill, all of it, in order:

  • step 0, grep patterns.md for the error signatures
  • step 1, evidence extraction into a facts table
  • step 2, classification into one primary family with its discriminator
  • step 3, research through the oracle-fusion-docs MCP first, then Customer Connect and Knowledge Base searches, every finding carrying its URL or Doc ID
  • step 4, at most four ranked hypotheses, each with a mechanism, a confidence percentage, one discriminating test and an in-instance verification path
  • step 5, convert the analysis into his keystrokes: only steps he runs himself, each with where exactly, done when, and a real time. Anything owned by Oracle, the client or a colleague is dropped from the list and carried by the message instead
  • step 6, write the message in full, as him, in the language of the destination, ready to paste

Respect the hard rules, in particular: no invented configuration values (phrase them as verification steps), no destructive diagnostics in PROD, verbatim error quotes, no em dashes, one ticket one mechanism, and no placeholder anywhere in a message.

Read the scope section of the skill before step 5. It is the section that decides what counts as a step: he reproduces, he diagnoses, he writes the message. He does not own the other bugs on the instance, the client's decisions, or production.

4. Deliver

Write the report to tickets/$ARGUMENTS/triage-report.md following the template in the hcm-debugging skill, then show it in the conversation.

In the conversation, lead with the two things that are actionable: the numbered steps he runs himself, and the message to send. The analysis stays in the file. Close with one line: the root cause in a sentence, and whether his move is investigate, send or wait.

Where the next fact comes from

Work the evidence ladder from the top, and stop at the first rung that settles the question: the dossier you already have, then the Oracle documentation, then a fact only the client can produce, then a read in DEV1, and only last a change in DEV1.

Documentation research is the first reflex, not a fallback. Quote the page verbatim with its URL when it describes the observed behaviour. Opening an instance is the expensive rung and has to earn its place. Asking the client for an extraction they alone can run is a legitimate answer, not a failure to investigate.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.