feat(aif-estimate-issue): story point calibration and blindspot detection skill - #89
Draft
guangshinhaha wants to merge 1 commit into
Draft
feat(aif-estimate-issue): story point calibration and blindspot detection skill#89guangshinhaha wants to merge 1 commit into
guangshinhaha wants to merge 1 commit into
Conversation
…etection skill Closes #87 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
natashaannn
requested changes
Jul 7, 2026
|
|
||
| Display the issue title and current body so the user can confirm this is the right issue before continuing. | ||
|
|
||
| ### Step 2: Detect the SP label convention and fetch calibration data |
Collaborator
There was a problem hiding this comment.
Unnecessary step to check for convention, skip checking for convention and use established story point convention of sp:<n>.
|
|
||
| If no SP labels are found in the repo, note this and skip calibration. The skill will still produce a complexity breakdown and blindspots checklist, but will flag that confidence is low due to missing historical data. | ||
|
|
||
| ### Step 3: Read the codebase |
Collaborator
There was a problem hiding this comment.
Replace this step with: If issue does not have relevant technical context and/or is still pending grooming, flag out for user and leave comment on github issue that this is still pending grooming and hence story points cannot be estimated.
|
|
||
| If no calibration data exists, base the estimate on the complexity analysis alone and clearly state that the estimate is uncalibrated. | ||
|
|
||
| ### Step 6: Generate blindspots checklist |
Collaborator
There was a problem hiding this comment.
Consider putting into aif-groom-issue skill; also consider folding whole skill into groom-issue-skill as these two skills are usually done in same grooming session .
Collaborator
|
@guangshinhaha Will convert this to draft, and will edit from here! |
natashaannn
marked this pull request as draft
July 8, 2026 03:38
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
aif-estimate-issueskill that calibrates story point estimates against a repo's historical SP-labeled issues and surfaces a blindspots checklist for grooming discussionssp:3,points:5), reads the codebase for complexity analysis, and outputs a structured estimate with comparable issues, a 6-dimension complexity breakdown, and missing considerationsai-sp:Nlabel so the team can reference the AI recommendation alongside their own estimateCloses #87
Test plan
aif-estimate-issueagainst an issue in a repo with existing SP labels (e.g. teacher-workspace) and verify it finds calibration anchorsai-sp:Nlabel is created and applied correctlyai-sp:*label--body-filewithout shell interpolation issues🤖 Generated with Claude Code