ttal-comment

Engineering Community

Repo stars 21
License MIT
Author repo ttal-cli

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: How agents use ttal comment for review workflows - plan reviews, PR reviews, triage reports, and verdicts. ttal comment is the u…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “Overview”, “Commands”, “Review Findings”, “Triage Pattern”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name ttal-comment directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “Overview / Commands / Review Findings” before expanding.

Boundaries And Review

Dependencies: It usually needs no extra API key, so start with a small validation task.
Permissions: Declared permissions include read / write; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

ttal-comment Skill

Overview

ttal comment is the unified tool for posting and reading review comments in the pipeline. Use it for plan reviews, PR reviews, triage reports, and verdicts.

Commands

ttal comment list                    # list all comments on current task
ttal comment get <round>             # read specific review round
ttal comment add "message"           # post comment (short messages)
ttal comment lgtm                    # approve current pipeline stage (reviewers only, auto-detects stage)

For multiline reports, use heredoc:

cat <<'REVIEW' | ttal comment add
## Review Findings
**Verdict:** Ready
REVIEW

Triage Pattern

When receiving a review comment with findings:

Read the comment: ttal comment list then ttal comment get <round>
Assess each finding: Fixed / Not Applicable / Remaining
Fix what needs fixing
Post a structured triage update:

cat <<'TRIAGE' | ttal comment add
## Triage Report (Round N)

**Fixed:**
- Issue 1 — what was done
- Issue 2 — what was done

**Not Applicable:**
- Issue 3 — why it doesn't apply

**Remaining:**
- Issue 4 — why it's deferred (or still being worked)
TRIAGE

If no remaining blocking issues: run ttal go <uuid> to advance the pipeline

After LGTM

When a reviewer posts LGTM with no remaining blocking issues:

Run ttal go <uuid> to advance the pipeline (reviewers use ttal comment lgtm which sets the tag automatically)
You do NOT need to post anything — the pipeline advances on the lgtm tag

Rules

Always post via ttal comment add — never output findings inline only
Use heredoc for any report longer than one line
Reviewers: always call ttal comment lgtm after approving — this sets the correct pipeline tag
Coders: after receiving LGTM, run ttal go <uuid> to finalize

Fluxly profile Author and license come from source; runtime, permissions, and network are Fluxly detections or estimates

Fluxly category: Engineering
Author-declared agents: No explicit declaration found; this is not inferred or tested compatibility
Static check: 94 / 100 · heuristic scan, not runtime safety proof
Author / version / license: @tta-lab · MIT
Fluxly token estimate: Lean
Fluxly setup estimate: Plug-and-play
External API key: No requirement detected
Detected OS requirements: Unspecified
Runtime requirements: Unspecified
Detected file/system behavior: Read-only
Write / modify
Detected network behavior: Local-only
Install commands: None (reference only)

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview ttal-comment.preview

The current SKILL.md does not define a fixed output example.

SKILL.md SKILL.md

# ttal-comment Skill

## Overview
ttal comment is the unified tool for posting and reading review comments in the pipeline. Use it for plan reviews, PR reviews, triage reports, and verdicts.

## Commands

```
ttal comment list                    # list all comments on current task
ttal comment get <round>             # read specific review round
ttal comment add "message"           # post comment (short messages)
ttal comment lgtm                    # approve current pipeline stage (reviewers only, auto-detects stage)
```

For multiline reports, use heredoc:
```
cat <<'REVIEW' | ttal comment add
## Review Findings
**Verdict:** Ready
REVIEW
```

## Triage Pattern

When receiving a review comment with findings:

1. Read the comment: `ttal comment list` then `ttal comment get <round>`
2. Assess each finding: Fixed / Not Applicable / Remaining
3. Fix what needs fixing
4. Post a structured triage update:

```
cat <<'TRIAGE' | ttal comment add
## Triage Report (Round N)

**Fixed:**
- Issue 1 — what was done
- Issue 2 — what was done

**Not Applicable:**
- Issue 3 — why it doesn't apply

**Remaining:**
- Issue 4 — why it's deferred (or still being worked)
TRIAGE
```

5. If no remaining blocking issues: run `ttal go <uuid>` to advance the pipeline

## After LGTM

When a reviewer posts LGTM with no remaining blocking issues:
- Run `ttal go <uuid>` to advance the pipeline (reviewers use `ttal comment lgtm` which sets the tag automatically)
- You do NOT need to post anything — the pipeline advances on the lgtm tag

## Rules

- Always post via `ttal comment add` — never output findings inline only
- Use heredoc for any report longer than one line
- Reviewers: always call `ttal comment lgtm` after approving — this sets the correct pipeline tag

…

Evidence boundary and execution chain

Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.

sections -> Overview → Commands → Review Findings → Triage Pattern → Triage Report (Round N) → After LGTM
terms    -> Verdict · Fixed · Not Applicable · Remaining
files/cmd -> ttal comment list · ttal comment get <round> · ttal go <uuid> · ttal comment lgtm · ttal comment add
body sha256 -> 44f669f257e5