I Just Deleted All My Agent Skills
Comments on “I Just Deleted All My Agent Skills”
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
A blogger reports deleting all their AI agent skills after reviewing benchmark evidence. One study of 98 public software engineering skills found 92 had no significant effect on coding results, and web development skills lowered pass rates while raising token costs by 72% to 394%.
Why it ranked
No. 39 of 46 with a score of 0.58. The panel rated it highest on practical relevance (0.75) and new information (0.70), lowest on technical depth (0.43). The judges disagreed most on overclaim (spread 0.58), so the story is marked contested. Placed No. 39, No. 32 by score alone: the 14th AI & machine learning story of the day (−0.080). The placement terms move stories; they are not part of the score.
- AI judgeJudge 2claude-haiku-5-5
- Opinion piece on AI agent skills drawing on several benchmarks it cites secondhand; practically relevant to builders of agents, but mostly aggregated links rather than primary evidence, with some overclaiming from a 'gut feeling' base.
- AI judgeJudge 3gpt-5.6-luna
- Relevant synthesis of agent-skill benchmarks, prompt minimization, and security findings, with concrete numbers and linked evidence. It is actionable but mostly summarizes others’ work and offers limited technical detail or reproducible methodology.
Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.
Score
0.58total under rubric v2.3Contestedjudges differ by 0.50 on new information, 0.58 on overclaim
- Significance0.51
- Reader interest0.69
- Audience breadth0.68
- Practical relevance0.75
- Substantiated0.59
- Technical depth0.43
- New information0.70
- Counts against: Promotional0.05
- Counts against: Overclaim0.43
Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).
| Question | Judge 1 | Judge 2 | Judge 3 | Mean | Spread | Weight | Contribution (weight times mean) |
|---|---|---|---|---|---|---|---|
| SignificanceHow much does this change what people in tech know or can do? | 0.57 | 0.35 | 0.60 | 0.51 | 0.25 | +0.24 | +0.122 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.68 | 0.60 | 0.80 | 0.69 | 0.20 | +0.26 | +0.180 |
| Audience breadthHow many people who build technology does it concern? | 0.69 | 0.55 | 0.80 | 0.68 | 0.25 | +0.13 | +0.088 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.80 | 0.70 | 0.75 | 0.75 | 0.10 | +0.22 | +0.165 |
| SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations. | 0.59 | 0.50 | 0.67 | 0.59 | 0.17 | +0.05 | +0.029 |
| Technical depthHow technically substantive is it? | 0.53 | 0.30 | 0.45 | 0.43 | 0.23 | +0.05 | +0.021 |
| New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)? | 0.81 | 0.40 | 0.90 | 0.70 | 0.50 , above the contested threshold | +0.05 | +0.035 |
| PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional. | 0.07 | 0.05 | 0.02 | 0.05 | 0.05 | −0.19 | −0.009 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.76 | 0.35 | 0.18 | 0.43 | 0.58 , above the contested threshold | −0.11 | −0.047 |
| Sum of contributions | +0.585 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.585 | ||||||
Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.
The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.
<a href="https://rubric.hrih.si/editions/2026-11-09/39/"><img src="https://rubric.hrih.si/badge/2026-11-09/39.svg" alt="Ranked #39 on Rubric, 9 Nov 2026" width="238" height="28"></a>Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 8 pts, not on front page
Recorded for context only, checked 9 Nov 2026, 05:46 UTC. It played no part in the ranking.