Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Implementation Tasks Generator · gotalab | DecimalAI

productivityby gotalab

Implementation Tasks Generator

gotalab/kiro-spec-tasks

Source gotalab/cc-sdd ↗License MIT

Generate implementation tasks for a specification

SkillScore68Maintained

Automatic

Project Management pack

Last verified 9/23/2026

What it changes

Passed 12 of 17 test cases with the skill, and 5 of 17 without it.

Without skill27%

With skill68%

Checks it passed that the model alone missed

Sets phase to `tasks-generated` in `spec.json`.
Keeps the overall final response concise and under 200 words.
Prompts the user to add numeric requirement IDs before generating tasks.

and 9 more in the full report

9 fixed6 passed either way7 still failing0 broke

Pass-rate lift: +41 pp
Tokens: +112%
Agent turns: 0%
Response time: -40%

Model gemini-3.6-flashMeasured 9/23/2026v915 of 22 cases passed with skill · 17 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/gotalab-kiro-spec-tasks/SKILL.md https://app.decimal.ai/s/gotalab-kiro-spec-tasks/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add gotalab-kiro-spec-tasks, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/gotalab-kiro-spec-tasks/ and pins it in .decimal/skills.lock

decimalai skills add gotalab-kiro-spec-tasks

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/gotalab-kiro-spec-tasks/SKILL.md https://app.decimal.ai/s/gotalab-kiro-spec-tasks/SKILL.md

Raw file: /s/gotalab-kiro-spec-tasks/SKILL.md ↗ · machine-readable summary at /s/gotalab-kiro-spec-tasks.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

In `tasks.md` for `email-worker`, we have core implementation sub-tasks and optional post-MVP test coverage tasks for non-critical edge cases. What standard markdown checkbox syntax marks these deferred testing sub-tasks?

What was checked, without and with the skill
Checked	Without skill	With skill
Uses the `- [ ]*` syntax for optional testing sub-tasks deferred post-MVP.	Passed	Passed
Restricts optional test task notation to test coverage satisfying already implemented acceptance criteria.	Missed	Passed

case-17 · gemini-3.6-flash · 9/23/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md188 linessingle file

Implementation Tasks Generator

<background_information>

Success Criteria:
- All requirements mapped to specific tasks
- Tasks properly sized (1-3 hours each)
- Clear task progression with proper hierarchy
- Natural language descriptions focused on capabilities
- A lightweight task-plan sanity review confirms the task graph is executable before tasks.md is written </background_information>

Step 1: Load Context

Read all necessary context:

{{KIRO_DIR}}/specs/$1/spec.json, requirements.md, design.md
{{KIRO_DIR}}/specs/$1/tasks.md (if exists, for merge mode)
Core steering context: product.md, tech.md, structure.md
Additional steering files only when directly relevant to requirements coverage, design boundaries, runtime prerequisites, or team conventions that affect task executability
Use explicitly requested skills and task-relevant local skills/playbooks, including design, accessibility, and UX. Select by description and read only needed guidance, even for small tasks; preserve required checks and host/project rules.

Validate approvals:

If -y flag provided: Auto-approve requirements and design in spec.json. Tasks approval is also handled automatically in Step 4.
Otherwise: Verify both approved (stop if not, see Safety & Fallback)
Determine sequential mode based on presence of --sequential

Step 2: Generate Implementation Tasks

Load generation rules and template:

Read rules/tasks-generation.md from this skill's directory for principles
If sequential is false: Read rules/tasks-parallel-analysis.md from this skill's directory for parallel judgement criteria
Read {{KIRO_DIR}}/settings/templates/specs/tasks.md for format (supports (P) markers)

Parallel Research

The following research areas are independent and can be executed in parallel:

Context loading: Spec documents (requirements.md, design.md), steering files
Rules loading: tasks-generation.md, tasks-parallel-analysis.md, tasks template

Track record

Benchmark

12 / 17

test cases passed, vs 5 / 17 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/23/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

gotalab / cc-sdd

tools/cc-sdd/templates/agents/antigravity-skills/skills/kiro-spec-tasks/SKILL.md

View on GitHub ↗

License MITImported 9/23/2026Version v9

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Implementation Tasks Generator

Step 1: Load Context

Step 2: Generate Implementation Tasks

Parallel Research

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills