tapd-iteration-report

Generates iteration changelogs and engineering efficiency reports from committed story records.

840|261|Updated Apr 18, 2019
One-click install
npx skills add https://github.com/TencentBlueKing/bk-bcs --skill tapd-iteration-report
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tapd-iteration-report
Source: https://github.com/TencentBlueKing/bk-bcs/tree/main/.agents/skills/tapd-iteration-runner/tapd-iteration-report
Command: npx skills add https://github.com/TencentBlueKing/bk-bcs --skill tapd-iteration-report

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, and includes references (resource) components.

What problem does it solve?

After all stories in an iteration are developed and committed, teams still need to manually assemble a version changelog, aggregate development efficiency metrics (code changes, duration, credit and token costs), clean up temporary files, and bump the patch version. This Skill automates that entire closing phase of the iteration pipeline.

Core Features & Use Cases

  • Changelog Generation: Scans each story's commit.md in sequence order and appends a versioned section (e.g., v0.9.3) to changelog.md without overwriting history.
  • Efficiency Metrics Aggregation: Reads iteration-state.json to produce a three-layer summary.md covering iteration totals, per-story statistics, and per-stage cost breakdowns (credit, input/output/cache tokens, call counts).
  • Iteration Housekeeping: Deletes the .tmp/ directory, increments the patch field in iteration-state.json, then commits and pushes results to the iteration branch.
  • Use Case: When every story in specs/v0.9.x reaches the committed phase, run this Skill to produce the v0.9.3 changelog and cost report, then push the finalized iteration branch to the remote repository.

Quick Start

Run the iteration report for specs/v0.9.x now that all stories are committed, generating the changelog and summary, then push the iteration branch.

Frequently Asked Questions about tapd-iteration-report

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a changelog from per-story commit records?

The Skill scans each story's commit.md under specs/${VERSION}/ in sequence order, extracts the Commit Message section, and appends a versioned chapter to changelog.md. Existing changelog content is preserved and new versions are appended.

What preconditions must be met before running an iteration report?

All stories in iteration-state.json must have phase set to committed, every story directory must contain a commit.md file, and the iteration status must be completed. If any condition fails, the Skill outputs an error and stops.

How are token and credit costs aggregated in the summary report?

Costs come from each story's stats.cost.per_stage fields, summed across stages and stories. The summary.md presents three layers: iteration totals, per-story statistics, and per-stage breakdowns with percentages.

What happens if stats.cost or duration_sec fields are missing?

Missing stats.cost, per_stage, or duration_sec fields are treated as zero for that story. The children field also tolerates null, empty object, or absent forms, so incomplete data does not break aggregation.

What happens when git push fails during the final commit step?

The Skill prompts you to check remote repository permissions and network connectivity while keeping the local commit intact. You can retry the push manually once the issue is resolved.